% % GENERATED FROM https://www.coli.uni-saarland.de % by : anonymous % IP : coli2006.lst.uni-saarland.de % at : Mon, 05 Feb 2024 15:41:11 +0100 GMT % % Selection : Year = 2002 % @InProceedings{Abramowicz_Piskorski:2002, AUTHOR = {Abramowicz, Witold and Piskorski, Jakub}, TITLE = {Information Extraction from Free Text Business Documents}, YEAR = {2002}, BOOKTITLE = {Proceedings of IRMA - Information Resources Management Association International Conference, May 19-22}, ADDRESS = {Seattle}, ABSTRACT = {One of the most difficult aspects of using search technology is the process of getting information in shape for searching. The objective of this paper is an investigation of the applicability of information extraction techniques in real-world business applications dealing with textual data since business relevant data is mainly transmitted through free-text documents. Further, we demonstrate an enormous indexing potential of lightweight linguistic text processing techniques applied in information extraction systems in other closely related fields of information technology which concern processing vast amounts of textual data.} } @InProceedings{Albrecht_et_al:2002, AUTHOR = {Albrecht, Irene and Haber, Jörg and Kähler, Kolja and Schröder, Marc and Seidel, Hans-Peter}, TITLE = {May I talk to you? :-) - Facial Animation from Text}, YEAR = {2002}, BOOKTITLE = {Proceedings of the 10th Pacific Conference on Computer Graphics and Applications (Pacific Graphics 2002), October 9-11}, EDITOR = {Coquillart, Sabine and Shum, Heung-Yeung and Hu, Shi-Min}, ADDRESS = {Tsinghua University, Beijing}, URL = {http://www.mpi-sb.mpg.de/resources/FAM/publ/pg2002.pdf}, ABSTRACT = {We introduce a facial animation system that produces real-time animation sequences including speech synchronization and non-verbal speech-related facial expressions from plain text input. A state-of-the-art text-to-speech synthesis component performs linguistic analysis of the text input and creates a speech signal from phonetic and intonation information. The phonetic transcription is additionally used to drive a speech synchronization method for the physically based facial animation. Further high-level information from the linguistic analysis such as different types of accents or pauses as well as the type of the sentence is used to generate non-verbal speech-related facial expressions such as movement of head, eyes, and eyebrows or voluntary eye blinks. Moreover, emoticons are translated into XML markup that triggers emotional facial expressions.}, ANNOTE = {COLIURL : Albrecht:2002:FAT.pdf} } @Misc{Avgustinova:2002, AUTHOR = {Avgustinova, Tania}, TITLE = {Review of: Goldsmith, John A., (Ed.): Phonological Theory: The Essential Readings. Blackwell Publishers, 1999. In: LINGUIST List 13.621. Thu, Mar 7 2002}, YEAR = {2002}, URL = {http://linguistlist.org/issues/13/13-621.html#1} } @InCollection{Avgustinova:2002_1, AUTHOR = {Avgustinova, Tania}, TITLE = {Clustering Clitics in Bulgarian Nominal Constituents}, YEAR = {2002}, BOOKTITLE = {Current Approaches to Formal Slavic Linguistics Contributions of the Second European Conference on Formal Description of Slavic Languages. FDSL II held at the University of Potsdam, November 20-22, 1997}, VOLUME = {9}, EDITOR = {Kosta, Peter and Frasek, Jens}, SERIES = {Linguistik International}, ADDRESS = {Frankfurt a. M., Berlin, Bern}, PUBLISHER = {Lang, Peter Frankfurt} } @InProceedings{Baldridge_Kruijff:2002, AUTHOR = {Baldridge, Jason and Kruijff, Geert-Jan M.}, TITLE = {Coupling CCG with Hybrid Logic Dependency Semantics}, YEAR = {2002}, BOOKTITLE = {Proceedings of the 40th Annual Meeting of the Association of Computational Linguistics (ACL'02), June 7-12}, ADDRESS = {University of Pennsylvania, Philadelphia} } @Book{Barry_Pützer:2002, AUTHOR = {Barry, William J. and Pützer, Manfred}, TITLE = {Festschrift für Max Mangold zum 80. Geburtstag}, YEAR = {2002}, VOLUME = {6}, SERIES = {PHONUS}, ADDRESS = {Universität des Saarlandes, Phonetik, Saarbrücken} } @InProceedings{Barry_Russo:2002, AUTHOR = {Barry, William J. and Russo, Michela}, TITLE = {Lamdacismo e Rotacismo in Area Napolitana: Realizzazione Fonetica e Posizione Fonologica}, YEAR = {2002}, BOOKTITLE = {Atti 29$^o$, Convegno Nazionale. Associazione Italiana di Acustica (AIA 2002), 12-14 giugno}, PAGES = {377-382}, EDITOR = {Pompoli, Roberto and Carletti, Eleonora and Fausti, Patrizio and Pedrielli, Francesca and Peretti, Alessandro and Pompoli, Francesco and Prodi, Nicola}, ADDRESS = {Ferrara, Italia} } @InProceedings{Becker_et_al:2002, AUTHOR = {Becker, Markus and Drozdzynski, Witold and Krieger, Hans-Ulrich and Piskorski, Jakub and Schäfer, Ulrich and Xu, Feiyu}, TITLE = {SProUT - Shallow Processing with Typed Feature Structures and Unification}, YEAR = {2002}, BOOKTITLE = {Proceedings of the International Conference on NLP (ICON 2002). December 18-21}, ADDRESS = {Mumbai, India}, URL = {http://www.dfki.de/~feiyu/sprout.pdf}, ABSTRACT = {We present SProUT, a platform for the development of multilingual shallow text processing systems. A grammar in SProUT consists of a set of rules, where the left-hand side is a regular expression over typed feature structures (TFSs), representing the recognition pattern, and the right-hand side is a sequence of TFSs, specifying how the output structure looks like. The reusable core components fo SProUT are a finite-state machine toolkit, a regular compiler, a typed feature structure package, and a finite-state machine interpreter.}, ANNOTE = {COLIURL : Becker:2002:SSP.pdf} } @InProceedings{Becker_Frank:2002, AUTHOR = {Becker, Markus and Frank, Anette}, TITLE = {A Stochastic Topological Parser of German}, YEAR = {2002}, BOOKTITLE = {Proceedings of the 19th Conference on Computational Linguistics (COLING'02), August 24 - September 1}, ADDRESS = {Taipei, Taiwan}, URL = {http://www.dfki.de/~frank/papers/Coling2002_Becker_Frank_245.ps}, ABSTRACT = {We present a new approach to topological parsing for German which is corpus-based, and built on a simple model of probabilistic CFG parsing. The topological field model is a theory-neutral model of clausal syntax that provides a linguistically motivated, but flat macro structure for complex sentences. Topological structures are highly compatible with deep syntactic analysis, thus perfectly suited for seamless integration of shallow and deep NLP. Besides the practical aspect of developing a robust and accurate topological parser, we investigate to what extent topological structures can be handled by context-free probabilistic models, while trying to detect specific phenomena that require more sophisticated models. We discuss experiments with systematic variants of a topological treebank grammar, which yield competitive results.}, ANNOTE = {COLIURL : Becker:2002:STP.pdf Becker:2002:STP.ps} } @InProceedings{Beil_et_al:2002, AUTHOR = {Beil, Franz and Prescher, Detlef and Schmid, Helmut and Schulte im Walde, Sabine}, TITLE = {Evaluation of the Gramotron Parser for German}, YEAR = {2002}, BOOKTITLE = {Proceedings of the LREC Workshop: Beyond PARSEVAL, May 29-31}, ADDRESS = {Las Palmas, Gran Canaria}, URL = {http://www.dfki.de/~prescher/papers/bib/2002lrec.beil.prescher.schmid.schulte_im_walde.pdf}, ABSTRACT = {The paper describes an experiment in inside-outside estimation of a lexicalized probabilistic context free grammar for German. Grammar and formalism features which make the experiment feasible are described. Successive models are evaluated on precision and recall of phrase markup consisting of labels for noun chunks and subcategorization frames. Our approach to parsing is a blend of symbolic and stochastic methods where we use evaluation results in both incremental grammar development and validation of selected output to be used in lexical semantic clustering. Our results are that (i) scrambling-style free phrase order, case morphology, subcategorization, and NP-internal gender, number and case agreement can be dealt within a lexicalized probabilistic context-free grammar formalism, and (ii) inside-outside estimation appears to be beneficial, however relies on a carefully built grammar and an evaluation based on carefully selected linguistic criteria. Additionally, we report experiments on overtraining with inside-outside estimation, especially focusing on comparison of the results of mathematical and linguistic evaluations.}, ANNOTE = {COLIURL : Beil:2002:EGP.pdf} } @InProceedings{Brants_et_al:2002, AUTHOR = {Brants, Sabine and Dipper, Stefanie and Hansen, Silvia and Lezius, Wolfgang and Smith, George}, TITLE = {The TIGER Treebank}, YEAR = {2002}, BOOKTITLE = {Proceedings of the Workshop on Treebanks and Linguistic Theories, September 20-21}, ADDRESS = {Sozopol, Bulgaria}, URL = {https://www.coli.uni-saarland.de/~sabine/tigertreebank.pdf}, ABSTRACT = {This paper reports on the TIGER Treebank, a corpus of currently 35.000 syntactically annotated German newspaper sentences. We describe what kind of information is encoded in the treebank and introduce the different representation formats that are used for the annotation and exploitation of the treebank. We explain the different methods used for the annotation: interactive annotation, using the tool (em Annotate), and LFG parsing. Furthermore, we give an account of the annotation scheme used for the TIGER treebank. This scheme is an extended and improved version of the NEGRA annotation scheme and we illustrate in detail the linguistic extensions that were made concerning the annotation in the TIGER project. The main differences are concerned with coordination, verb-subcategorization, expletives as well as proper nouns. In addition, the paper also presents the query tool TIGERSearch that was developed in the project to exploit the treebank in an adequate way. We describe the query language which was designed to facilitate a simple formulation of complex queries; furthermore, we shortly introduce TIGERin, a graphical user interface for query input. The paper concludes with a summary and some directions for future work.}, ANNOTE = {COLIURL : Brants:2002:TT.pdf} } @InProceedings{Brants_Hansen:2002, AUTHOR = {Brants, Sabine and Hansen, Silvia}, TITLE = {Developments in the TIGER Annotation Scheme and their Realization in the Corpus}, YEAR = {2002}, BOOKTITLE = {Proceedings of the 3rd International Conference on Language Resources and Evaluation (LREC-2002), May 29-31}, ADDRESS = {Las Palmas de Gran Canaria, Spain}, URL = {https://www.coli.uni-saarland.de/~sabine/brants-hansen.pdf}, ABSTRACT = {This paper presents the annotation of the German TIGER Treebank. First, issues concerning the annotation, representation as well as querying of the treebank are discussed. Within this context, the annotation tool ANNOTATE, the export and XML formats of the TIGER Treebank and the TIGER search tool are briefly introduced. Secondly, the developments of the TIGER annotation scheme and their realization in the corpus are introduced focussing on the differences between the underlying NEGRA annotation scheme and the further developed TIGER annotation scheme. The main differences are concerned with verb-subcategorization, coordination, appositions and parentheses as well as proper nouns. Thirdly, the annotation scheme is assessed through an evaluation and a problem discussion of the above mentioned changes. For this purpose, inter- annotator agreement in the TIGER project has been analyzed focussing on exactly these changes. This analysis shows where the annotators' decision problems are. These difficulties are discussed in greater detail on the basis of annotation examples. The paper concludes with some suggestions for the improvement of the TIGER annotation scheme.}, ANNOTE = {COLIURL : Brants:2002:DTA.pdf} } @InProceedings{Buitelaar:2002, AUTHOR = {Buitelaar, Paul}, TITLE = {Lexical Semantics in the Age of the Semantic Web – Invited Talk}, YEAR = {2002}, BOOKTITLE = {Proceedings of the Conference of the Slovenian Society for Language Technologies, 14 - 15th October 2002}, PAGES = {6 - 10}, EDITOR = {Erjavec, Tomaz and Gros, Jerneja}, ADDRESS = {Ljubljana, Slovenia}, URL = {http://dfki.de/~paulb/sdjt02.ps}, ABSTRACT = {Lexical semantics is the study of word meaning. The semantic web is a vision of what the web could be if it would foremost consist of knowledge (structured data) rather than text or other unstructured data as it is today. This paper is about the future of word meaning if the semantic web becomes a reality. First, I will therefore briefly clarify what the semantic web vision consists of, followed by a sketch of lexical semantics. Finally, I will speculate on how the inherent semantic standardization process of the semantic web could have a dramatic influence on the study and use of word meaning.}, ANNOTE = {COLIURL : Buitelaar:2002:LSA.pdf} } @InProceedings{Buitelaar_Sacaleanu:2002, AUTHOR = {Buitelaar, Paul and Sacaleanu, Bogdan}, TITLE = {Extending Synsets with Medical Terms}, YEAR = {2002}, BOOKTITLE = {Proceedings of the 1st International WordNet Conference, January 21-25}, ADDRESS = {Mysore, India}, URL = {http://dfki.de/~paulb/gwa.pdf}, ABSTRACT = {An important problematic issue with general semantic lexicons like WordNet or GermaNet is that they do not cover many terms and concepts specific to certain domains. Therefore, these resources need to be tuned to a specific domain at hand. This involves selecting those senses that are most appropriate for the domain, as well as extending the sense inventory with novel terms and novel senses that are specific to the domain. In this paper we focus on extending GermaNet synsets with domain specific terms, taking into account the domain relevance of senses (i.e. synsets).}, ANNOTE = {COLIURL : Buitelaar:2002:ESM.pdf} } @InProceedings{Busemann:2002, AUTHOR = {Busemann, Stephan}, TITLE = {Issues in Generating from Interlingua Representations}, YEAR = {2002}, BOOKTITLE = {Proceedings of the 1st International Workshop on UNL, other Interlinguas and their Applications}, PAGES = {1-7}, EDITOR = {Tovar, Edmundo and Gallardo, Carolina}, ADDRESS = {Las Palmas}, URL = {ftp://lt-ftp.dfki.uni-sb.de/pub/papers/local/interlingua.entry ftp://lt-ftp.dfki.uni-sb.de/pub/papers/local/interlingua.pdf}, ABSTRACT = {Multi-lingual generation starts from non-linguistic content representations for generating texts in different languages that are equivalent in meaning. In contrast, cross-lingual generation is based on a language-neutral content representation which is the result of a linguistic analysis process. Non-linguistic representations do not reflect the structure of the text. Quite differently, language-neutral representations express functor-argument relationships and other semantic properties found by the underlying analysis process. These differences imply diverse generation tasks. In this contribution, we relate multi-lingual to cross-lingual generation and discuss emergent problems for the definition of an interlingua.}, ANNOTE = {COLIURL : Busemann:2002:IGI.pdf} } @Proceedings{Stephan:2002, TITLE = {Proceedings der 6. Konferenz zur Verarbeitung natürlicher Sprache (KONVENS 2002), 30. September - 2. Oktober}, YEAR = {2002}, NUMBER = {D-02-01}, EDITOR = {Busemann, Stephan}, SERIES = {DFKI Document}, ADDRESS = {Saarbrücken, Germany}, PUBLISHER = {German Research Center for AI (DFKI)}, URL = {http://konvens2002.dfki.de/cd/inhalt/index.html}, ABSTRACT = {Die Konferenz zur Verarbeitung natürlicher Sprache (KONVENS) wird seit 1992 in zweijährigem Turnus von den wissenschaftlichen Fachgesellschaften DEGA, DGfS, GI, GLDV, ITG und ÖGAI ausgerichtet. Die KONVENS stellt einen wichtigen Kristallisationspunkt für die Veröffentlichung wissenschaftlicher Ergebnisse in der Sprachverarbeitung dar. Im Jahr 2002 wird die nunmehr sechste KONVENS von der GI, Fachgruppe Natürlichsprachliche Systeme'', in Saarbrücken veranstaltet. Themen der wissenschaftlichen Konferenz sind alle Bereiche der maschinellen Verarbeitung von natürlicher Sprache in gesprochener als auch in geschriebener Form. Die Tagung verfolgt das Ziel, einen breiten Querschnitt durch die aktuelle Forschung und Entwicklung im Gebiet der Sprachverarbeitung zu bieten - unter Einschluss aller relevanten Disziplinen wie Computerlinguistik, Sprachtechnologie, Kognitions-Psychologie, Informatik, Akustik und Nachrichtentechnik. Beiträge aus der gesamten Bandbreite zwischen Forschung, Entwicklung, Anwendung und Evaluation von natürlichsprachlichen Ressourcen, Komponenten und Systemen waren in Form unveröffentlichter Forschungs- und Entwicklungsergebnisse oder innovativer industrieller Anwendungen willkommen. 44 Papiere wurden eingereicht und von je zwei Mitgliedern des Programmkomitees begutachtet, die teilweise weitere Gutachter hinzuzogen. In diesem Begutachtungsverfahren wählte das Programmkomitee 22 Beiträge als Vorträge und 11 als Poster zur Präsentation während der Tagung und zur Veröffentlichung aus. Zudem konnten zwei hochrangige Wissenschaftler gewonnen werden, ihre aktuellen Arbeiten in Form eingeladener Vorträge vorzustellen. Christiane Fellbaum (Princeton University und Berlin-Brandenburgische Akadamie der Wissenschaften) beschreibt Arbeiten zur Repräsentation idiomatischer Wendungen im Lexikon und lexikalischen Datenbanken (WordNet). Matthew Crocker (Universität des Saarlandes) zieht Verbindungen zwischen Psycholinguistik und statistischer Computerlinguistik. Der vorliegende Tagungsband enthält Kurzfassungen der eingeladenen Vorträge sowie die angenommenen Vorträge und Poster. Im Namen des Programmkomitees danke ich herzlich allen Autorinnen und Autoren, die durch ihre Einreichung ein interessantes und anspruchsvolles Tagungsprogramm ermöglichten. Besonders möchte ich den beiden eingeladenen Vortragenden, Christiane Fellbaum und Matthew Crocker, für ihre Beiträge danken. Dem Gastgeber der Konferenz, der DFKI GmbH, gebührt Dank für die Bereitstellung der Räumlichkeiten, der Infrastruktur sowie von Arbeitskraft. Bei der Erstellung der Webseite http://konvens2002.dfki.de und des vorliegenden Tagungsbandes haben Carmen Görl und Matthias Rinck wesentlich mitgewirkt. Das Konferenz-Sekretariat wurde von Corinna Johanns geleitet, die nicht nur die finanzielle Seite der Konferenz betreute, sondern sich auch um die lukullischen und touristischen Aspekte kümmerte: der halbtägige Ausflug nach Nennig und zur Villa Borg mit abendlichem Bankett führt uns in beiderlei Hinsicht auf römische Spuren im Saarland. Allen Mitwirkenden danke ich sehr herzlich für ihr besonderes Engangement, ohne das diese Tagung nicht möglich gewesen wäre. Ausdrücklich möchte ich allen Mitgliedern des Programmkomitees für die effiziente und reibungslose Zusammenarbeit beim Zustandekommen des Tagungsprogramms danken.} } @InCollection{Callmeier:2002, AUTHOR = {Callmeier, Ulrich}, TITLE = {Preprocessing and Encoding Techniques in PET}, YEAR = {2002}, BOOKTITLE = {Collaborative Language Engineering. A Case Study in Efficient Grammar-based Processing}, EDITOR = {Oepen, Stephan and Flickinger, Dan and Tsujii, Jun-ichi and Uszkoreit, Hans}, ADDRESS = {Stanford}, PUBLISHER = {CSLI Publications} } @InProceedings{Capstick_et_al:2002, AUTHOR = {Capstick, Joanne and Declerck, Thierry and Erbach, Gregor and Jameson, Anthony and Jörg, Brigitte and Karger, Reinhard and Uszkoreit, Hans and Wahlster, Wolfgang and Wegst, Tillmann}, TITLE = {COLLATE: Competence Center in Speech and Language Technology}, YEAR = {2002}, BOOKTITLE = {Proceedings of the 3rd International Conference on Language Resources an Evaluation (LREC'02), May 28-31}, ADDRESS = {Las Palmas, Canary Islands, Spain}, URL = {https://www.coli.uni-saarland.de/~erbach/pub/collate_lrec_2002.pdf}, ABSTRACT = {This paper presents the structure and activitities of the recently established Competence Center in Speech and Language Technology in Saarbrücken. The objectives of the Competence Center are to provide a comprehensive information service about speech and language technologies, including live demonstrations of the most important language technology (LT) systems, and to advance the state of the art in the evaluation of LT systems for realworld applications. The Competence Center comprises the following components: 1. the Virtual Information Center Language Technology World (www.ltworld.org), the world's most comprehensive information resource about speech and language technology 2. the Demonstration Center in Saarbrücken, which offers interested parties the possibility to play and experiment with different speech and language technologies, or to attend guided demonstrations, 3. the Evaluation Center, which conducts evaluations of the overall usability of language technology systems and advances knowledge of relevant usability issues and evaluation methods. The work presented in this paper was carried out by the German Research Center for Artificial Intelligence in collaboration with Saarland University in the context of the project COLLATE (COmputational Linguistics and LAnguage TEchnology for Real Life Applications), funded by the German Federal Ministry of Education and Research (www.bmbf.de).}, ANNOTE = {COLIURL : Capstick:2002:CCC.pdf} } @InProceedings{Carroll_et_al:2002, AUTHOR = {Carroll, John and Frank, Anette and Lin, Dekang and Prescher, Detlef and Uszkoreit, Hans}, TITLE = {Introductory pages of the editors}, YEAR = {2002}, BOOKTITLE = {Beyond PARSEVAL - Towards Improved Evaluation Measures for Parsing Systems. Workshop at the 3rd International Conference on Language Resources and Evaluation (LREC'02), May 28}, EDITOR = {Carroll, John and Frank, Anette and Lin, Dekang and Prescher, Detlef and Uszkoreit, Hans}, ADDRESS = {Las Palmas, Gran Canaria, Spain}, URL = {http://www.dfki.de/dfkibib/publications/docs/intro.ps}, ANNOTE = {COLIURL : Carroll:2002:IPE.pdf Carroll:2002:IPE.ps} } @Book{John_et_al:2002, TITLE = {Beyond PARSEVAL - Towards Improved Evaluation Measures for Parsing Systems. Workshop at the 3rd International Conference on Language Resources and Evaluation (LREC-02)}, YEAR = {2002}, EDITOR = {Carroll, John and Frank, Anette and Lin, Dekang and Prescher, Detlef and Uszkoreit, Hans}, ADDRESS = {Las Palmas, Gran Canaria, Spain}, URL = {http://www.cogs.susx.ac.uk/lab/nlp/carroll/papers/beyond-proceedings.pdf}, ANNOTE = {COLIURL : Carroll:2002:BPT.pdf} } @Article{Corley_Scheepers:2002, AUTHOR = {Corley, Martin and Scheepers, Christoph}, TITLE = {Syntactic Priming in English Sentence Production: Categorical and Latency Evidence from an Internet-Based Study}, YEAR = {2002}, JOURNAL = {Psychonomic Bulletin and Review}, VOLUME = {9}, NUMBER = {1}, PAGES = {126-131} } @InCollection{Crocker_Corley:2002, AUTHOR = {Crocker, Matthew W. and Corley, Steffan}, TITLE = {Modular Architectures and Statistical Mechanisms: The Case from Lexical Category Disambiguation}, YEAR = {2002}, BOOKTITLE = {The Lexical Basis of Sentence Processing}, EDITOR = {Merlo, Paola and Stevenson, Suzanne}, ADDRESS = {Amsterdam}, PUBLISHER = {John Benjamins} } @InProceedings{Crysmann_et_al:2002, AUTHOR = {Crysmann, Berthold and Frank, Anette and Kiefer, Bernd and Krieger, Hans-Ulrich and Müller, Stefan and Neumann, Günter and Piskorski, Jakub and Schäfer, Ulrich and Siegel, Melanie and Uszkoreit, Hans and Xu, Feiyu}, TITLE = {An Integrated Architecture for Shallow and Deep Processing}, YEAR = {2002}, BOOKTITLE = {Proceedings of ACL-2002, Association for Computational Linguistics 40th Anniversary Meeting, July 7-12}, ADDRESS = {Philadelphia, USA}, URL = {http://www.dfki.de/~feiyu/wb-acl02.pdf http://www.dfki.de/~neumann/publications/new-ps/wb-acl02.pdf}, ANNOTE = {COLIURL : Crysmann:2002:IAS.pdf} } @Article{Duchier:2002, AUTHOR = {Duchier, Denys}, TITLE = {Dominance Constraints with Boolean Connectives: A Model-Eliminative Treatment}, YEAR = {2002}, JOURNAL = {Journal of Theoretical Computer Science}, VOLUME = {293}, NUMBER = {2}, PAGES = {321-343}, URL = {ftp://ftp.ps.uni-sb.de/pub/papers/ProgrammingSysLab/duchier-dcbc2000.ps.gz}, ABSTRACT = {Dominance constraints are a language of tree descriptions. Tree descriptions are widely used in computational linguistics for talking and reasoning about trees. While previous research has focused on the conjunctive fragment, we now extend the account to all Boolean connectives and propose a new formalism that combines dominance constraints with a feature tree logic. Although the satisfiability problem in the conjunctive fragment is known to be NP-complete, we have previously demonstrated that it can be addressed very effectively by constraint propagation: we developed an encoding that transforms a dominance constraint into a constraint satisfaction problem on finite sets solvable by constraint programming. We present a generalization of this encoding for our more expressive formalism, and prove soundness and completeness. Our main contribution is a treatment of disjunction suitable for constraint propagation.}, ANNOTE = {COLIURL : Duchier:2002:DCB.pdf Duchier:2002:DCB.ps} } @Book{Eckert_Barry:2002, AUTHOR = {Eckert, Hartwig and Barry, William J.}, TITLE = {The Phonetics and Phonology of English Pronunciation. A Coursebook with CD-Rom}, YEAR = {2002}, PAGES = {289}, ADDRESS = {Trier}, PUBLISHER = {Wissenschaftlicher Verlag Trier (WVT)}, ABSTRACT = {This self-study book takes the reader on a journey of discovery into the areas of pronunciation, phonetics, and phonology; places where students have often lost their way – and their motivation. The book is structured in the way people learn: Examples and immediate practice in the spoken and written medium illustrate and consolidate newly acquired linguistic knowledge, improving and strengthening listening and pronunciation skills, and raising language awareness. Since hard work without motivating support is difficult to sustain, the relative importance and usefulness of the different phonetic phenomena are explained, and pictures, cartoons, jokes, old and new limericks and dialogues are used to raise and maintain students' interest and help them to remember important distinctions in a complex subject matter which is not always immediately accessible to the uninitiated. As the table of contents reveals, the book has a highly modularized structure, which is suited to selective remedial practice, and helps in the revision of particular problem areas. There is a great variety of exercises – ear-training, discrimination exercises, problem solving, phonetic transcription, etc. – for beginners and advanced students. Solutions are provided at the end of the book, and there is an index for quick reference to technical terms. The file structure of the CD-ROM facilitates quick access to any exercise in any order.} } @InCollection{Egg:2002, AUTHOR = {Egg, Markus}, TITLE = {Beginning Novels and Finishing Hamburgers - Remarks on the Semantics of to begin}, YEAR = {2002}, BOOKTITLE = {Ereignisstrukturen}, VOLUME = {76}, EDITOR = {Dölling, Johannes and Zybatow, Tatjana}, SERIES = {Linguistische Arbeitsberichte}, ADDRESS = {Leipzig}, PUBLISHER = {Universität Leipzig}, ABSTRACT = {Verbs like begin may take either a VP or an NP complement, but their meaning is pretty similar in both cases, e.g., for begin, the start of an eventuality is at stake. Pustejovsky's approach captures this similarity in terms of an invariant meaning of the verb, which entails a process of reinterpretation for the transitive variant of the verb. I will show that while the intuitions of this proposal are on the right track, its actual implementation suffers from a number of shortcomings. I will offer an analysis that preserves Pustejovsky's intuition but avoids these shortcomings. My analysis is based on an appropriate underspecifcation formalism.}, NOTE = {Sumitted} } @Article{Egg:2002_1, AUTHOR = {Egg, Markus}, TITLE = {Semantic Construction for Reinterpretation Phenomena}, YEAR = {2002}, JOURNAL = {Linguistics}, VOLUME = {40}, PAGES = {579-609} } @InProceedings{Egg_Erk:2002, AUTHOR = {Egg, Markus and Erk, Katrin}, TITLE = {A Compositional Account of VP Ellipsis}, YEAR = {2002}, BOOKTITLE = {Proceedings of the 8th International Conference on Head-Driven Phrase Structure Grammar, August 3-5}, PAGES = {162-179}, EDITOR = {Van Eynde, Frank and Hellan, Lars and Beermann, Dorothee}, ADDRESS = {Stanford}, PUBLISHER = {CSLI Publications}, URL = {ftp://ftp.ps.uni-sb.de/pub/papers/ProgrammingSysLab/ellhpsg01.ps.gz}, ABSTRACT = {We present an approach to VP ellipsis that allows the direct derivation of source and target sentences (the former need not be unique) during semantic construction. Specific syntactic constituent structures are associated with ellipsis potential, which can then be discharged by pro-verbs like 'did (too)'. The determination of source and target sentence, which is done with semantic features in an HPSG framework, is coupled with a comprehensive analysis of ellipsis, which also handles its interaction with scope and anaphora.}, ANNOTE = {COLIURL : Egg:2002:CAV.pdf Egg:2002:CAV.ps} } @InProceedings{Erk_Kruijff:2002, AUTHOR = {Erk, Katrin and Kruijff, Geert-Jan M.}, TITLE = {A Constraint-Programming Approach to Parsing with Resource-Sensitive Categorial Grammar}, YEAR = {2002}, BOOKTITLE = {Proceedings of the 7th International Workshop on Natural Language Understanding and Logic Programming (NLULP'02), July 28}, EDITOR = {Wintner, Shuly}, ADDRESS = {Copenhagen, Denmark}, PUBLISHER = {Computer Science Department, Roskilde University}, URL = {http://www.cs.haifa.ac.il/~shuly/nlulp02/papers/ErkKruijff.pdf}, ABSTRACT = {Parsing with resource-sensitive categorial grammars (up to the Lambek-Van Benthem calculus LP) is an NP-complete problem. The traditional approach to parsing with such grammars is based on generate & test and cannot avoid this high worst-case complexity. This paper proposes an alternative approach, based on constraint programming: Given a grammar, constraints formulated on an abstract interpretation of the grammar's logical structure are used to prune the search space during parsing. The approach is provably sound and complete, and reduces the search space in steps that are mostly linear or low-polynomial.}, ANNOTE = {Erk:2002:CPA} } @InProceedings{Fiedler_Gabsdil:2002, AUTHOR = {Fiedler, Armin and Gabsdil, Malte}, TITLE = {Supporting Progressive Refinement of Wizard-of-Oz Experiments}, YEAR = {2002}, BOOKTITLE = {6th International Conference on Intelligent Tutoring Systems (ITS '02). Workshop on Empirical Methods for Tutorial Dialogue, June 4}, PAGES = {62-69}, EDITOR = {Rose, Carolyn Penstein and Aleven, Vincent}, ADDRESS = {San Sebastian, Spain}, URL = {http://www.ags.uni-sb.de/~afiedler/pubs/papers/its-02-ws.ps.gz http://www.ags.uni-sb.de/~afiedler/pubs/papers/its-02-ws.pdf http://www.ags.uni-sb.de/~afiedler/pubs/papers/its-02-ws.bib}, ABSTRACT = {We present the architecture of DiaWoZ, a system supporting the design and execution of Wizard-of-Oz experiments to collect data from tutorial dialogues. The architecture is highly modular and allows for the progressive refinement of the experiments by both designing increasingly sophisticated dialogues and successively replacing simulated components of the tutoring system by actual implementations. The dialogues to be examined are specified in a language that combines finite-state approaches with information states, thereby allowing for great flexibility. Therefore, the architecture should also be appropriate for examining dialogues in general.}, ANNOTE = {COLIURL : Fiedler:2002:SPR.pdf Fiedler:2002:SPR.ps} } @InProceedings{Fliedner:2002, AUTHOR = {Fliedner, Gerhard}, TITLE = {A System for Checking NP Agreement in German Texts}, YEAR = {2002}, BOOKTITLE = {Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL'02), July 6-12. Companion Volume of the Conference Proceedings. Proceedings of the Student Workshop, Demonstration Abstracts and Tutorial Abstracts}, PAGES = {12-17}, ADDRESS = {University of Pennsylvania, Philadelphia}, URL = {http://acl.ldc.upenn.edu/acl2002/STUDENT/pdfs/Student887.pdf}, ABSTRACT = {In this paper, we describe the design, implementation, and evalutation of a system for checking NP agreement in German texts. We use shallow parsing based on finite state automata in combination with constraint relaxation and a method for parse ranking based on optimality theory. The system's grammar was developed and tested over a reference corpus of about 800,000 words to ensure robustness and broad coverage. When evaluated against a corpus of approximately 200,000 words, the system reached recall and precision values around the 67,\% mark.} } @InProceedings{Frank:2002, AUTHOR = {Frank, Anette}, TITLE = {A (Discourse) Functional Analysis of Asymmetric Coordination}, YEAR = {2002}, BOOKTITLE = {Proceedings of the 7th International Lexical Functional Grammar Conference (LFG'02), July 3-5}, ADDRESS = {Athens, Greece}, ABSTRACT = {A long-standing puzzle in coordination is the so-called SGF-coordination (Subject Gap in Finite/Fronted constructions) in German (1), first discussed b y (Hoehle 1983). Its syntactic analysis is challenging, since the subject (Jaeger, man) is realised in the middle field in the left conjunct, and is thus - under standard analyses of constituent coordination - not accessible from within the second conjunct, which is missing a subject (hence subject gap). (1) a. In den Wald ging der Jaeger und fing einen Hasen. Into the forest went the hunter and caught a rabbit The hunter went into the forest and caught a rabbit (1) b. Nimmt man den Deckel ab und ruehrt die Fuellung um, steigen Daempfe auf. Takes one the cover off and stirrs the stuffing, steam rises. If one takes the cover off and stirrs the stuffing, steam will rise. SGF constructions have been analysed in terms of asymmetrically embedded conjuncts (Wunderlich 1988, Hoehle 1990, Heycock and Kroch 1993, Buering und Hartmann 1998) or symmetric conjuncts (Steedman 1990, Kathol 1995,1999). Asymmetric embedding is problematic as it involves extraction asymmetries, or a doubtful analysis of coordination as adjunction. Symmetric analyses assume special licensing conditions which are not independently motivated. Especially the word order conditions of Kathol's analysis lack any independent syntactic motivation, and fail to account for related asymmetric coordinations of verb-last and verb-fronted (VL/VF) sentences (2). (2) Wenn Du in ein Kaufhaus kommst und (Du) hast kein Geld, kannst Du nichts kaufen. if you in a shop come and you have no money can you nothing buy If you enter a shop and (you) don't have any money, you can't buy anything. We present a multi-factorial LFG analysis of asymmetric constructions (1) and (2), which relies on independently motivated principles of the correspondences between c-structure, f-structure, and i-structure (information structure). SGF coordination is analysed as symmetric coordination in c-structure. Binding of the (prima facie) inaccessible subject of the first conjunct is enabled, at the level of f-structure, by asymmetric projection of a grammaticalised discourse function GDF, a topic or subject function (Bresnan, 2001). Asymmetric GDF projection is motivated by relating the semantic and discourse-functional properties of asymmetric coordination to well-known discourse subordination effects of modal subordination. In conjunction with word order constraints in the optimality model of (Choi 1999, 2001), our analysis explains some mysterious word order constraints as well as some puzzling scoping properties.}, NOTE = {in October} } @InCollection{Frank_Zaenen:2002, AUTHOR = {Frank, Anette and Zaenen, Annie}, TITLE = {Tense in LFG: Syntax and Morphology}, YEAR = {2002}, BOOKTITLE = {How we say WHEN it happens. Contributions to the theory of temporal reference in natural language}, EDITOR = {Kamp, Hans and Reyle, Uwe}, ADDRESS = {Tübingen}, PUBLISHER = {Max Niemeyer Verlag}, URL = {http://www.dfki.de/~frank/papers/tensemorph-final.ps.gz}, ANNOTE = {COLIURL : Frank:2002:TLS.pdf} } @InProceedings{Gabsdil_et_al:2002, AUTHOR = {Gabsdil, Malte and Koller, Alexander and Striegnitz, Kristina}, TITLE = {Natural Language and Inference in a Computer Game}, YEAR = {2002}, BOOKTITLE = {19th International Conference on Computational Linguistics (COLING '02), August 24 - September 1}, ADDRESS = {Taipei, Taiwan}, URL = {https://www.coli.uni-saarland.de/~koller/papers/game-nl.ps.gz}, ABSTRACT = {We present an engine for text adventures -- computer games with which the player interacts using natural language. The system employs current methods from computational linguistics and an efficient inference system for description logic to make the interaction more natural. The inference system is especially useful in the linguistic modules dealing with reference resolution and generation and we show how we use it to rank different readings in the case of referential and syntactic ambiguities. It turns out that the player's utterances are naturally restricted in the game scenario, which simplifies the language processing task.}, ANNOTE = {COLIURL : Gabsdil:2002:NLI.pdf Gabsdil:2002:NLI.ps} } @Article{Grice:2002, AUTHOR = {Grice, Martine}, TITLE = {Discussion paper: Dainora : An Empirically Based Probabilistic Model of Intonation in American English}, YEAR = {2002}, JOURNAL = {Glot International} } @Article{Grice:2002_1, AUTHOR = {Grice, Martine}, TITLE = {Review of: Botinis (ed): Intonation: Analysis, Modelling and Technology}, YEAR = {2002}, JOURNAL = {Computational Linguistics}, VOLUME = {28}, NUMBER = {1}, PAGES = {87-89} } @Article{Grice_Baumann:2002, AUTHOR = {Grice, Martine and Baumann, Stefan}, TITLE = {Deutsche Intonation und GToBI}, YEAR = {2002}, JOURNAL = {Linguistische Berichte}, VOLUME = {191}, PAGES = {267-298}, URL = {https://www.coli.uni-saarland.de/phonetik/projects/Tobi/lingber-gtobi-2.pdf}, ABSTRACT = {In this paper we provide an overview of work carried out on the intonation of Standard German both in auditory phonetic studies and in the instrumentally-based phonological accounts within the autosegmental-metrical framework. We examine how far the different accounts shed light on controversial issues such as leading tones, levels of phrasing, and phrase accents and propose a surface-oriented annotation framework, GToBI, which aims to capture all empirically observed distinctive intonation patterns. For illustration purposes, the contours which are reported to occur most commonly are given in schematic form, along with their GToBI transcription and examples of their usage.}, ANNOTE = {COLIURL : Grice:2002:DIG.pdf} } @PhdThesis{Hansen:2002, AUTHOR = {Hansen, Silvia}, TITLE = {The Nature of Translated Text - An Interdisciplinary Methodology for the Investigation of the Specific Properties of Translations}, YEAR = {2002}, ADDRESS = {Saarbrücken, Germany}, SCHOOL = {Institute for Applied Linguistics - Translation and Interpreting, Saarland University} } @InProceedings{Hansen_Teich:2002, AUTHOR = {Hansen, Silvia and Teich, Elke}, TITLE = {The creation and exploitation of a translation reference corpus}, YEAR = {2002}, BOOKTITLE = {Proceedings of the First International Workshop on Language Resources for Translation Work and Research (3rd International Conference on Language Resources and Evaluation (LREC-2002)), May 28}, ADDRESS = {Las Palmas de Gran Canaria, Spain}, URL = {https://www.coli.uni-saarland.de/~hansen/hansen-teich.zip}, ABSTRACT = {While in many branches of linguistics monolingual reference corpora are widely used, e.g., in lexicography, in the construction of grammars and generally in empirical linguistic studies, in translation research as well as translation practice the concept of a parallel refernce corpus has not yet assumed a similarly important role. In our view, this is partly due to a lack of interaction of researchers involved in the development of corpus tools (computational linguistics, humanities computing) and the potential users of such tools in the area of translation (translatology, translation practice). The goal of the present paper is to initiate such an interaction. We present the design of an German-English and French-English translation corpus and explore its use as a reference corpus for translatologists as well as translators. First, we introduce the the basic computational techniques needed to build such a translation reference corpus. These techniques cover the preparation of the corpus as well as its linguistic annotation. In the preparatory step the corpus has to be aligned and encoded. To enrich the corpus with linguistic information, part-of-speech tagging and syntactic parsing have to be carried out for the different languages. Furthermore, to make the parallel reference corpus usable for translation scholars and translators, it has to be searchable, i.e., appropriate query facilities must be provided. We show how to extract instances of linguistic phenomena that are of interest from a translation point of view using a multilingual English-German-French corpus. We explain possible translation procedures for perfect aspect, reduced relative clauses and cleft constructions from English into German and French on the basis of parallel concordances extracted from the translation reference corpus. Finally, we specify some additional requirements to improve the usability of translation corpora in both translation studies and translation practice.} } @InProceedings{Karagjosova_Kruijff-Korbayová:2002, AUTHOR = {Karagjosova, Elena and Korbayova, Ivana}, TITLE = {An Analysis of Conditional Responses in Dialogue}, YEAR = {2002}, BOOKTITLE = {5th International Conference on TEXT, SPEECH and DIALOGUE (TSD 2002), September 9-12}, PAGES = {317-320}, EDITOR = {Sojka, Petr and Kopecek, Ivan and Pala, Karel}, SERIES = {Lecture Notes in Artificial Intelligence LNCS/LNAI 2448}, ADDRESS = {Brno, Czech Republic}, PUBLISHER = {Springer Verlag}, URL = {http://coli.uni-sb.de/~elka/Papers/tsd02-final.ps}, NOTE = {forthcoming}, ANNOTE = {COLIURL : Karagjosova:2002:ACR.pdf Karagjosova:2002:ACR.ps} } @InProceedings{Karagjosova_Kruijff-Korbayova:2002_1, AUTHOR = {Karagjosova, Elena and Korbayova, Ivana}, TITLE = {Conditional Responses in Information Seeking Dialogues}, YEAR = {2002}, BOOKTITLE = {3rd SIGdial Workshop on Discourse and Dialogue, July 11-12}, PAGES = {84-87}, EDITOR = {Jokinen, Kristiina and McRoy, Susan}, ADDRESS = {ACL,Philadelphia, Pennsylvania, USA}, URL = {http://coli.uni-sb.de/~elka/Papers/sigdial-final.ps}, NOTE = {forthcoming}, ANNOTE = {COLIURL : Karagjosova:2002:CRI.pdf Karagjosova:2002:CRI.ps} } @InProceedings{Kasper_Steffen:2002, AUTHOR = {Kasper, Walter and Steffen, Jörg}, TITLE = {Multilingual flexible and robust summarization}, YEAR = {2002}, BOOKTITLE = {Proceedings der 6. Konferenz zur Verarbeitung natürlicher Sprache (KONVENS 2002), 30. September - 2. Oktober}, PAGES = {215-218}, EDITOR = {Busemann, Stephan}, SERIES = {DFKI Document D-02-01}, ADDRESS = {Saarbrücken, Germany}, PUBLISHER = {German Research Center for AI (DFKI)}, URL = {http://konvens2002.dfki.de/cd/pdf/44P-steffen.pdf}, ABSTRACT = {SumEx is multilingual, flexible and robust system for automatic text summarization following a sentence extraction approach. The paper presents an overview of this system.}, ANNOTE = {COLIURL : Kasper:2002:MFR.pdf} } @InProceedings{Keller_et_al:2002, AUTHOR = {Keller, Frank and Lapata, Mirella and Ourioupina, Olga}, TITLE = {Using the Web to Overcome Data Sparseness}, YEAR = {2002}, BOOKTITLE = {Proceedings of the Conference on Empirical Methods in Natural Language Processing}, PAGES = {230-237}, EDITOR = {Hajic, Jan and Matsumoto, Yuji}, ADDRESS = {Philadelphia, USA}, URL = {http://www.iccs.informatics.ed.ac.uk/~keller/papers/emnlp02.pdf}, ABSTRACT = {This paper shows that the web can be employed to obtain frequencies for bigrams that are unseen in a given corpus. We describe a method for retrieving counts for adjective-noun, noun-noun, and verb-object bigrams from the web by querying a search engine. We evaluate this method by demonstrating that web frequencies and correlate with frequencies obtained from a carefully edited, balanced corpus. We also perform a task-based evaluation, showing that web frequencies can reliably predict human plausibility judgments.}, ANNOTE = {COLIURL : Keller:2002:UWO.pdf} } @InCollection{Kiefer_Krieger:2002, AUTHOR = {Kiefer, Bernd and Krieger, Hans-Ulrich}, TITLE = {A Context-Free Approximation of Head-Driven Phrase Structure Grammar}, YEAR = {2002}, BOOKTITLE = {Collaborative Language Engineering. A Case Study in Efficient Grammar-Based Processing}, EDITOR = {Oepen, Stephan and Flickinger, Dan and Tsujii, Jun-ichi and Uszkoreit, Hans}, ADDRESS = {Stanford}, PUBLISHER = {CSLI Publications}, ABSTRACT = {We present a context-free approximation of unification-based grammars, such as HPSG or PATR-II. The theoretical underpinning is established through a least fixpoint construction over a certain monotonic function. In order to reach a finite fixpoint, the concrete implementation can be parameterized in several ways, either by specifying a finite iteration depth, by using different restrictors, or by making the symbols of the CFG more complex adding annotations à la GPSG. We also present several methods that speed up the approximation process and help to limit the size of the resulting CF grammar.} } @InProceedings{Kiefer_et_al:2002, AUTHOR = {Kiefer, Bernd and Krieger, Hans-Ulrich and Prescher, Detlef}, TITLE = {A Novel Disambiguation Method For Unification-Based Grammars Using Probabilistic Context-Free Approximations}, YEAR = {2002}, BOOKTITLE = {Proceedings of the 19th International Conference on Computational Linguistics (COLING'02), August 24 - September 1}, ADDRESS = {Taipei, Taiwan}, URL = {http://www.dfki.de/dfkibib/publications/docs/paper-alternative-font2}, ABSTRACT = {We present a novel disambiguation method for unificationbased grammars (UBGs). In contrast to other methods, our approach obviates the need for probability models on the UBG side in that it shifts the responsibility to simpler contextfree models, indirectly obtained from the UBG. Our approach has three advantages: (i) training can be effectively done in practice, (ii) parsing and disambiguation of contextfree readings requires only cubic time, and (iii) involved probability distributions are mathematically clean. In an experiment for a midsize UBG, we show that our novel approach is feasible. Using unsupervised training, we achieve 88% accuracy on an exactmatch task.}, ANNOTE = {COLIURL : Kiefer:2002:NDM.pdf Kiefer:2002:NDM.ps} } @Proceedings{Alexander_Gideon:2002, TITLE = {Proceedings of the Student Research Workshop at ACL-02, July 7-12}, YEAR = {2002}, EDITOR = {Koller, Alexander and Mann, Gideon}, ADDRESS = {Philadelphia, Pennsylvania, USA} } @InCollection{Koller_Niehren:2002, AUTHOR = {Koller, Alexander and Niehren, Joachim}, TITLE = {Constraint Programming in Computational Linguistics}, YEAR = {2002}, BOOKTITLE = {Words, Proofs, and Diagrams}, EDITOR = {Barker-Plummer, Dave and Beaver, David I. and van Benthem, Johan and di Luzio, Patrick Scotto}, ADDRESS = {Stanford}, PUBLISHER = {CSLI Press}, URL = {http://www.ps.uni-sb.de/Papers/abstracts/CP-NL.html ftp://ftp.ps.uni-sb.de/pub/papers/ProgrammingSysLab/CP-NL.ps.gz}, ABSTRACT = {Constraint programming is a programming paradigm that was originally invented in computer science to deal with hard combinatorial problems. Recently, constraint programming has evolved into a technology which permits to solve hard industrial scheduling and optimization problems. We argue that existing constraint programming technology can be useful for applications in natural language processing. Some problems whose treatment with traditional methods requires great care to avoid combinatorial explosion of (potential) readings seem to be solvable in an efficient and elegant manner using constraint programming. We illustrate our claim by two recent examples, one from the area of underspecified semantics and one from parsing.}, NOTE = {Extended version of a paper at the 8th Stanford Workshop on Logic, Language, and Computation (1999)}, ANNOTE = {COLIURL : Koller:2002:CPC.pdf Koller:2002:CPC.ps} } @InProceedings{Koller_Striegnitz:2002, AUTHOR = {Koller, Alexander and Striegnitz, Kristina}, TITLE = {Generation as Dependency Parsing}, YEAR = {2002}, BOOKTITLE = {Proceedings of the 40th Anniversary Meeting of the Association of Computational Linguistics (ACL2002), July 6-12}, ADDRESS = {University of Pennsylvania, Philadelphia}, URL = {https://www.coli.uni-saarland.de/cl/projects/indigen/papers/acl2002.ps.gz https://www.coli.uni-saarland.de/~koller/papers/gen-dg.ps.gz}, ABSTRACT = {Natural-Language Generation from flat semantics is an NP-complete problem. This makes it necessary to develop algorithms that run with reasonable efficiency in practice despite the high worst-case complexity. We show how to convert TAG generation problems into dependency parsing problems, which is useful because optimizations in recent dependency parsers based on constraint programming tackle exactly the combinatorics that make generation hard. Indeed, initial experiments display promising runtimes.}, ANNOTE = {COLIURL : Koller:2002:GDP.pdf Koller:2002:GDP.ps} } @InProceedings{Kordoni:2002, AUTHOR = {Kordoni, Valia}, TITLE = {Participle-Adjective Formation in Modern Greek}, YEAR = {2002}, BOOKTITLE = {Proceedings of the 7th International Lexical-Functional Grammar Conference (LFG'02), July 3-5}, PAGES = {220-238}, EDITOR = {Butt, Miriam and King, Tracy Holloway}, ADDRESS = {National Technical University of Athens, Athens, Greece}, PUBLISHER = {CSLI Publications. Stanford (ISSN 1098-6782)}, URL = {https://www.coli.uni-saarland.de/~kordoni/papers/lfg02kordoni-num.pdf}, ANNOTE = {Kordoni:2002:PAF} } @Article{Kordoni:2002_1, AUTHOR = {Kordoni, Valia}, TITLE = {Modern Greek Psych Verb Constructions}, YEAR = {2002}, JOURNAL = {Recherches en linguistique grecque}, VOLUME = {Tome 2}, URL = {https://www.coli.uni-saarland.de/~kordoni/papers/valia-kordoni.doc}, ABSTRACT = {This paper presents a semantic analysis for Psych Verb Constructions in Modern Greek.}, ANNOTE = {COLIURL : Kordoni:2002:MGP.pdf} } @InProceedings{Korthals_Debusmann:2002, AUTHOR = {Korthals, Christian and Debusmann, Ralph}, TITLE = {Linking Syntactic and Semantic Arguments in a Dependency-based formalism}, YEAR = {2002}, BOOKTITLE = {Proceedings of the 19th International Conference on Computational Linguistics (COLING'02), August 24 - September 1}, ADDRESS = {Taipei, Taiwan}, URL = {http://www.ps.uni-sb.de/~rade/papers/coling02.pdf}, ANNOTE = {COLIURL : Korthals:2002:LSS.pdf} } @InProceedings{Krenn_et_al:2002, AUTHOR = {Krenn, Brigitte and Grice, Martine and Piwek, Paul and Schröder, Marc and Klesen, Martin and Baumann, Stefan and Pirker, Hannes and van Deemter, Kees and Gstrein, Erich}, TITLE = {Generation of Multi-Modal Dialogue for Net Environments}, YEAR = {2002}, BOOKTITLE = {Proceedings der 6. Konferenz zur Verarbeitung natürlicher Sprache (KONVENS 2002), 30. September - 2. Oktober}, PAGES = {91-98}, EDITOR = {Busemann, Stephan}, SERIES = {DFKI Document D-02-01}, ADDRESS = {Saarbrücken, Germany}, PUBLISHER = {German Research Center for AI (DFKI)} } @InProceedings{Krenn_et_al:2002_1, AUTHOR = {Krenn, Brigitte and Gstrein, Erich and Neumayr, Barbara and Grice, Martine}, TITLE = {What Can We Learn from Users of Avatars in Net Environments?}, YEAR = {2002}, BOOKTITLE = {Proceedings of AAMAS 2002 Workshop:Embodied Conversational Agents - Let's Specify and Evaluate Them!, July 15-16}, ADDRESS = {Bologna, Italy}, URL = {http://www.vhml.org/workshops/AAMAS/papers/krenn.pdf}, ABSTRACT = {In this paper we describe a commercial application of a net environment, and present the user data we have collected so far from three launches of this application. A net environment in our definition is a virtual space inhabited by avatars which have been created and are subsequently visited and instructed by users via the internet. Net environments are a useful means for studying user behaviour in general, and they are particularly well suited for presentation of multimedia content and systematic gathering of user responses on the appropriateness or effectiveness of the different presentations.}, ANNOTE = {COLIURL : Krenn:2002:WCW.pdf} } @InCollection{Kruijff-Korbayová_et_al:2002, AUTHOR = {Korbayova, Ivana and Bateman, John and Kruijff, Geert-Jan M.}, TITLE = {Generation of Contextually Appropriate Word Order}, YEAR = {2002}, BOOKTITLE = {Information Sharing: Reference and Presupposition in Language Generation and Interpretation}, VOLUME = {143}, PAGES = {193-222}, EDITOR = {Kibble, Rodger and van Deemter, Kees}, SERIES = {CSLI Lecture Notes}, ADDRESS = {Stanford}, PUBLISHER = {CSLI Publications}, ANNOTE = {COLIURL : Kruijff-Korbayova:1999:GCA.pdf Kruijff-Korbayova:1999:GCA.ps} } @InProceedings{Kruijff-Korbayová_et_al:2002_1, AUTHOR = {Korbayova, Ivana and Karagjosova, Elena and Larsson, Staffan}, TITLE = {Enhancing Collaboration with Conditional Responses in Information Seeking Dialogues}, YEAR = {2002}, BOOKTITLE = {Proceedings of the 6th Workshop on the Semantics and Pragmatics of Dialogue, September 4-6}, PAGES = {93-100}, EDITOR = {Bos, Johan and Foster, Mary Ellen and Matheson, Colin}, ADDRESS = {Edinburgh University, UK}, ANNOTE = {COLIURL : Kruijff-Korbayova:2002:ECC.pdf Kruijff-Korbayova:2002:ECC.ps} } @InProceedings{Kurz_Xu:2002, AUTHOR = {Kurz, Daniela and Xu, Feiyu}, TITLE = {Text Mining for the Extraction of Domain Relevant Terms and Term Collocations}, YEAR = {2002}, BOOKTITLE = {Proceedings of the International Workshop on Computational Approaches to Collocations}, ADDRESS = {Vienna}, URL = {http://www.dfki.de/dfkibib/publications/docs/Kurz_2002_TMEDRTTC.pdf}, ABSTRACT = {This paper provides a system which combines classification-based term extraction method with the statistical collocation calculations.}, ANNOTE = {COLIURL : Kurz:2002:TME.pdf} } @InProceedings{Lenci_et_al:2002, AUTHOR = {Lenci, Alessandro and Bartolini, Roberto and Calzolari, Nicoletta and Agua, Ana and Busemann, Stephan and Cartier, Emmanuel and Chevreau, Karine and Coch, José}, TITLE = {Multilingual Summarization by Integrating Linguistic Resources in the MLIS-MUSI Project}, YEAR = {2002}, BOOKTITLE = {Proceedings of the 3rd International Conference on Language Resources and Evaluation (LREC'02), May 29-31}, ADDRESS = {Las Palmas, Canary Islands, Spain}, URL = {ftp://lt-ftp.dfki.uni-sb.de/pub/papers/local/MUSI_paper_LREC2002.pdf}, ABSTRACT = {In this paper we will illustrate the approach to multilingual automatic abstract production adopted by the EUsponsored project MLIS MUSI. Although a small scale research project, MUSI has tried to tackle the challenges set by multilingual summarization by adopting an original approach based on the definition of a shared ontology and representation language, and on the reuse of existing linguistic resources. MUSI combines a statisticbased module for relevant sentence extraction and a conceptbased component to generate multilingual summaries.}, ANNOTE = {COLIURL : Lenci:2002:MSI.pdf} } @InCollection{Maedche_et_al:2002, AUTHOR = {Maedche, Alexander and Neumann, Günter and Staab, Steffen}, TITLE = {Bootstrapping an Ontology-based Information Extraction System. Studies in Fuzziness and Soft Computing}, YEAR = {2002}, BOOKTITLE = {Intelligent Exploration of the Web}, EDITOR = {Szczepaniak, Piotr and Segovia, Javier and Kacprzyk, Janusz and Zadeh, Lofti A.}, ADDRESS = {Berlin}, PUBLISHER = {Springer}, URL = {http://www.dfki.de/~neumann/publications/new-ps/bootstrapping.pdf}, ABSTRACT = {Automatic intelligent web exploration will benefit from shallow information extraction techniques if the latter can be brought to work within many different domains. The major bottleneck for this, however, lies in the so far difficult and expensive modeling of lexical knowledge, extraction rules, and an ontology that together define the information extraction system. In this paper we present a bootstrapping approach that allows for the fast creation of an ontologybased information extracting system relying on several basic components, viz. a core information extraction system, an ontology engineering environment and an inference engine. We make extensive use of machine learning techniques to support the semi-automatic, incremental bootstrapping of the domain-specific target information extraction system.}, ANNOTE = {COLIURL : Maedche:2002:BOB.pdf} } @InProceedings{Müller:2002, AUTHOR = {Müller, Karin}, TITLE = {Evaluating Syllabification: One Category Shared by Many Grammars}, YEAR = {2002}, BOOKTITLE = {Proceedings of the Workshop of the Third International Conference on Language Resources and Evaluation (LREC2002), May 29-31}, EDITOR = {Setzer, Andrea and Gaizauskas, Robert}, ADDRESS = {Las Palmas, Canary Islands, Spain}, URL = {https://www.coli.uni-saarland.de/~kmueller/Onlinepapers/LREC02.ps}, ABSTRACT = {We apply a series of contextfree grammars to syllabification by using a supervised training method. In our experiments, we investigate various phonological grammars, which strongly differ in structure. A simple evaluation metric word accuracy supports grammar development by denoting an increasing performance for grammars enriched with linguistic structure. This evaluation, judging one single category shared by all grammars, is in strong contrast to PARSEVAL, which is designed for a single grammar evaluating (almost) all categories. Using a toytreebank, we show that the PARSEVAL measures are hard to interpret, since the results are inconsistent with one another. It turns out that evaluating only a limited number of categories (here only one single category) is a harder evaluation measure than measuring the precision of all occurring substructures of a grammar.}, ANNOTE = {COLIURL : Muller:2002:ESO.pdf Muller:2002:ESO.ps} } @InProceedings{Müller:2002_1, AUTHOR = {Müller, Karin}, TITLE = {Probabilistic Context-Free Grammars for Phonology}, YEAR = {2002}, BOOKTITLE = {Workshop on Morphological and Phonological Learning at Association for Computational Linguistics 40th Anniversary Meeting (ACL-02), July 6-12}, ADDRESS = {University of Pennsylvania, Philadelphia, USA}, URL = {https://www.coli.uni-saarland.de/~kmueller/Onlinepapers/SIGPHON02.ps}, ABSTRACT = {We present a phonological probabilistic context free grammar, which describes the word and syllable structure of German words. The grammar is trained on a large corpus by a simple supervised method, and evaluated on a syllabification task achieving 96.88% word accuracy on word to kens, and 90.33% on word types. We added rules for English phonemes to the grammar, and trained the enriched grammar on an English corpus. Both grammars are evaluated qualitatively showing that probabilistic contextfree grammars can contribute linguistic knowledge to phonology. Our formal approach is multilingual, while the training data is languagedependent.}, ANNOTE = {COLIURL : Muller:2002:PCF.pdf Muller:2002:PCF.ps} } @InProceedings{Müller:2002_2, AUTHOR = {Müller, Stefan}, TITLE = {The Morphology of German Particle Verbs: Solving the Bracketing Paradox}, YEAR = {2002}, BOOKTITLE = {Proceedings of the HPSG-2001 Conference, Norwegian University of Science andTechnology, August 3-5}, PAGES = {247-266}, EDITOR = {Van Eynde, Frank and Hellan, Lars and Beermann, Dorothee}, ADDRESS = {Trondheim}, PUBLISHER = {CSLI Publications}, URL = {http://cslipublications.stanford.edu/HPSG/2/Mueller-pn.pdf http://www.dfki.de/~stefan/PS/paradox.ps.gz http://www.dfki.de/~stefan/PS/paradox.pdf}, ABSTRACT = {Inflectional affixes are sensitive to morphological properties of the elements they attachto. Therefore Bierwisch (1987) suggested that the inflectional material is combinedwith both the verbal stem of simplex verbs and the verbal stem of particle verbs. Heargued that this leads to the bracketing paradox in the case of particle verbs since thesemantic contribution of the inflectional information scopes over the semantic contri-bution of the complete particle verb. This paradox will be discussed in section 2.1.In section 2.2, I will discuss nominalizations and adjective derivation, which are alsoproblematic because of various bracketing paradoxes. In section 3 I will suggest a solu-tion to these apparent paradoxes that assumes that inflectional and derivational prefixesand suffixes always attach to a form of a stem that contains the information about a pos-sible particle already, but without containing a phonological realization of the particle.The particle is a dependent of the verb and is combined with its head after inflectionand derivation. With such an approach no rebracketing for the analysis of particle verbsmechanisms are necessary.}, ANNOTE = {COLIURL : Muller:2002:MGP.pdf Muller:2002:MGP.ps} } @InCollection{Müller:2002_3, AUTHOR = {Müller, Stefan}, TITLE = {Syntax or Morphology: German Particle Verbs Revisited}, YEAR = {2002}, BOOKTITLE = {Verb-Particle Explorations}, VOLUME = {1}, PAGES = {119-139}, EDITOR = {Dehé, Nicole and Jackendoff, Ray and McIntyre, Andrew and Urban, Silke}, SERIES = {Interface Explorations}, ADDRESS = {Berlin}, PUBLISHER = {Mouton de Gruyter}, URL = {http://www.dfki.de/~stefan/PS/dfki-report-mouton.ps.gz}, ABSTRACT = {In diesem Aufsatz untersuche ich einige Argumente, die in der Literatur benutzt wurden, um zu zeigen, daß Partikelverben als morphologische Objekte zu analysieren sind. Ich zeige, daß die Nichttransparenz mancher Partikelverben kein Kriterium dafür ist, daß Partikelverben morphologische Objekte sind, daß die Partikel unter bestimmten Voraussetzungen vorfeldfähig ist und daß auch bei Verbletztstellung die Partikel vom Verb getrennt im Mittelfeld stehen kann. Außerdem zeige ich, daß hinter am auch syntaktische Verbindungen stehen, können, so daß man nicht davon ausgehen kann, daß hinter am nur Wörter stehen können. Mit diesem Test haben andere Autoren versucht zu zeigen, daß Partikelverben Wörter und somit morphologische Objekte sind.}, ANNOTE = {COLIURL : Muller:2002:SMG.pdf Muller:2002:SMG.ps} } @InCollection{Müller:2002_4, AUTHOR = {Müller, Stefan}, TITLE = {Complex Predicates: Verbal Complexes, Resultative Constructions, and Particle Verbs in German}, YEAR = {2002}, BOOKTITLE = {Studies in Constraint-Based Lexicalism}, ADDRESS = {Stanford}, PUBLISHER = {CSLI Publications}, URL = {http://www.dfki.de/~stefan/PS/complex.ps.gz http://www.essex.ac.uk/linguistics/clmt/papers/hpsg/mueller.pdf}, ABSTRACT = {In this book, I develop a theory of complex predicates that accounts for normal copula constructions, subject and object predicatives, secondary predicates like depictives (1) and resultative constructions (2), and particle verbs. (1) Er ißt das Fleisch roh. (2) Er fährt das Auto kaputt / zu Schrott. In the part about particle verbs it is argued that particles should be treated as parts of the predicate complex. They are serialized in the right sentence bracket (3)-(4) and they can be fronted like adjectives or verbs (5). (3) Karl kommt abends in Berlin an. (4) Karl kommt abends in der Stadt an, in der ich wohne. (5) Fest steht, daß Karl nicht der Mörder war. So it seems reasonable to treat the preverb-verb-constructions in the same way as other predicate complex constructions. Frontings as (5) then can be described as instances of Partial Verb Phrase Fronting.}, ANNOTE = {COLIURL : Muller:2002:CPV.pdf} } @InProceedings{Müller:2002_5, AUTHOR = {Müller, Stefan}, TITLE = {Multiple Constituents in the Vorfeld}, YEAR = {2002}, BOOKTITLE = {The 7th conference on Formal Grammar (FG 2002), 3-4 August}, PAGES = {113-124}, EDITOR = {Jäger, Gerhard and Monachesi, Paola and Penn, Gerald and Winter, Shuly}, ADDRESS = {Trento, Italy}, URL = {http://www.dfki.de/~stefan/PS/mehr-vf.pdf}, NOTE = {URL Vorentwurf in deutscher Sprache}, ANNOTE = {COLIURL : Muller:2002:MCV.pdf} } @InProceedings{Müller:2002_6, AUTHOR = {Müller, Stefan}, TITLE = {Mehrfache Vorfeldbesetzung}, YEAR = {2002}, BOOKTITLE = {Proceedings der 6. Konferenz zur Verarbeitung natürlicher Sprache (KONVENS 2002), 30. September - 2. Oktober}, PAGES = {115-122}, EDITOR = {Busemann, Stephan}, SERIES = {DFKI Document D-02-01}, ADDRESS = {Saarbrücken, Germany}, PUBLISHER = {German Research Center for AI (DFKI)}, URL = {http://www.dfki.de/~stefan/PS/konvens2002.pdf}, ABSTRACT = {In diesem Aufsatz wird gezeigt, daß das Voranstellen von mehreren Konstituenten vor das finite Verb im Deutschen möglich ist, obwohl das Deutsche normalerweise als Verbzweitsprache klassifiziert wird. Es wird eine HPSG-Analyse entwickelt, die die Konstituenten im Vorfeld als zusammengehörige Einheit analysiert und diese Einheit in Bezug zu einem Verb setzt.}, ANNOTE = {COLIURL : Muller:2002:MV.pdf} } @InProceedings{Nederhof_Satta:2002, AUTHOR = {Nederhof, Mark-Jan and Satta, Giorgio}, TITLE = {Parsing Non-Recursive Context-Free Grammars}, YEAR = {2002}, BOOKTITLE = {Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL ANNUAL'02), July 7-12}, PAGES = {112-119}, ADDRESS = {Philadelphia, Pennsylvania, USA}, URL = {http://www.dfki.de/dfkibib/publications/docs/nederhof02d.ps}, ABSTRACT = {We consider the problem of parsing nonrecursive contextfree grammars, i.e., contextfree grammars that generate finite languages. In natural language processing, this problem arises in several areas of application, including natural language generation, speech recognition and machine translation. We present two tabular algorithms for parsing of nonrecursive contextfree grammars, and show that they perform well in practical settings, despite the fact that this problem is PSPACE complete.}, ANNOTE = {COLIURL : Nederhof:2002:PNR.pdf Nederhof:2002:PNR.ps} } @InCollection{Neumann:2002, AUTHOR = {Neumann, Günter}, TITLE = {Data-driven Approaches to Head-driven Phrase Structure Grammar}, YEAR = {2002}, BOOKTITLE = {Introduction to Data-oriented Parsing}, EDITOR = {Bod, Rens and Scha, Remko and Sima'an, Khahil}, ADDRESS = {Stanford}, PUBLISHER = {CSLI Publications}, URL = {http://www.dfki.de/~neumann/publications/new-ps/hpsg-dop-main.pdf}, ABSTRACT = {We present HPSG–DOP, a method for automatically extracting a Stochastic Lexicalized Tree Grammar (SLTG) from a HPSG source grammar and a given corpus.1 Processing of a SLTG is performed by a specialized fast parser. The approach has been tested on a large English grammar and has been shown to achieve additional performance increase compared to parsing with a highly tuned HPSG parser. Our approach is simple and transparent. The extracted grammars are declaratively represented and have a high degree of practical applicability.}, ANNOTE = {COLIURL : Neumann:2002:DDA.pdf} } @InCollection{Neumann:2002_1, AUTHOR = {Neumann, Günter}, TITLE = {Programming Languages in Artificial Intelligence}, YEAR = {2002}, BOOKTITLE = {Encyclopedia of Information Systems}, EDITOR = {Bentley and Bidgoli}, ADDRESS = {San Diego}, PUBLISHER = {Academic Press}, URL = {http://www.dfki.de/~neumann/publications/new-ps/ai-pgr.pdf}, ANNOTE = {COLIURL : Neumann:2002:PLA.pdf} } @InProceedings{Neumann_Flickinger:2002, AUTHOR = {Neumann, Günter and Flickinger, Dan}, TITLE = {HPSG-DOP: Data-Oriented Parsing with HPSG}, YEAR = {2002}, BOOKTITLE = {Proceedings of the 9th International Conference on HPSG (HPSG-2002), August 8-9}, ADDRESS = {Kyung Hee University, Seoul}, URL = {http://www.dfki.de/~neumann/publications/new-ps/hpsg-dop-short.pdf}, ANNOTE = {COLIURL : Neumann:2002:HDD.pdf} } @Article{Neumann_Piskorski:2002, AUTHOR = {Neumann, Günter and Piskorski, Jakub}, TITLE = {A Shallow Text Processing Core Engine}, YEAR = {2002}, JOURNAL = {Journal of Computational Intelligence}, VOLUME = {18}, NUMBER = {3}, URL = {http://www.dfki.de/~neumann/publications/new-ps/comp-intell.pdf}, NOTE = {to appear}, ANNOTE = {COLIURL : Neumann:2002:STP.pdf} } @InProceedings{Neumann_Schäfer:2002, AUTHOR = {Neumann, Günter and Schäfer, Ulrich}, TITLE = {Whiteboard - Eine XML-basierte Architektur für die Analyse natürlichsprachlicher Texte}, YEAR = {2002}, BOOKTITLE = {Proceedings of Online 2002, 25th European Congress Fair for Technical Communication Düsseldorf}, VOLUME = {C}, PAGES = {635.01-635.12}, EDITOR = {Jänichen, Stefan}, ADDRESS = {Düsseldorf, Deutschland}, PUBLISHER = {Online GmbH Kongresse und Messen für technische Kommunikation}, URL = {http://www.dfki.de/~neumann/publications/new-ps/Whiteboard-DFKI-online2002.pdf}, ANNOTE = {COLIURL : Neumann:2002:WXB.pdf} } @Article{Neumann_Schmeier:2002, AUTHOR = {Neumann, Günter and Schmeier, Sven}, TITLE = {Shallow Natural Language Technology and Text Mining}, YEAR = {2002}, JOURNAL = {Künstliche Intelligenz. The German Artificial Intelligence Journal}, URL = {http://www.dfki.de/~neumann/publications/new-ps/ki-tm-final.rtf}, NOTE = {to appear} } @InProceedings{Oepen_et_al:2002, AUTHOR = {Oepen, Stephan and Bender, Emily and Callmeier, Ulrich and Flickinger, Dan and Siegel, Melanie}, TITLE = {Parallel Distributed Grammar Engineering for Practical Applications}, YEAR = {2002}, BOOKTITLE = {Proceedings of the 19th International Conference on Computational Linguistics}, ADDRESS = {Taipei, Taiwan}, URL = {http://www-csli.stanford.edu/~bender/papers/gee13.pdf}, ABSTRACT = {Based on a detailed case study of parallel grammar development distributed across two sites, we review some of the requirements for regression testing in grammar engineering, summarize our approach to systematic competence and performance profiling, and discuss our experience with grammar development for a commercial application. If possible, the workshop presentation will be organized around a software demonstration.}, ANNOTE = {COLIURL : Oepen:2002:PDG.pdf} } @Book{Stephan_et_al:2002, TITLE = {Collaborative Language Engineering. A Case Study in Efficient Grammar-based Processing}, YEAR = {2002}, PAGES = {300}, EDITOR = {Oepen, Stephan and Flickinger, Dan and Tsujii, Jun-ichi and Uszkoreit, Hans}, SERIES = {CSLI Lecture Notes}, ADDRESS = {Stanford}, PUBLISHER = {CSLI Publications}, ABSTRACT = {Following high hopes and subsequent disillusionment in the late 1980s, the past decade of work in language engineering has seen a dramatic increase in the power and sophistication of statistical approaches to natural language processing, along with a growing recognition that these methods alone cannot meet the full range of demands for applications of NLP. While statistical methods, often described as 'shallow' processing techniques, can bring real advantages in robustness and efficiency, they do not provide the precise, reliable representations of meaning which more conventional symbolic grammars can supply for natural language. A consistent, fine-grained mapping between form and meaning is of critical importance in some NLP applications, including machine translation, speech prosthesis, and automated email response. Recent advances in grammar development and processing implementations offer hope of meeting these demands for precision. This volume provides an update on the state of the art in the development and application of broad-coverage declarative grammars built on sound linguistic foundations -- the 'deep' processing paradigm -- and presents several aspects of an international research effort to produce comprehensive, re-usable grammars and efficient technology for parsing and generating with such grammars.} } @InProceedings{Oravecz_Dienes:2002, AUTHOR = {Oravecz, Csaba and Dienes, Peter}, TITLE = {Efficient Stochastic Part-of-Speech Tagging for Hungarian}, YEAR = {2002}, BOOKTITLE = {Proceedings of the Third International Conference on Language Resources and Evaluation (LREC2002), May 29-31}, PAGES = {710-717}, ADDRESS = {Las Palmas, Canary Islands, Spain}, URL = {https://www.coli.uni-saarland.de/~dienes/oravecz_dienes_02.ps.gz}, ABSTRACT = {Many of the methods developed for Western European languages and used widespread to produce annotated language resources cannot readily be applied to Central and Eastern European languages, due to the large number of novel phenomena exhibited in the syntax and morphology of these languages, which these methods have to handle but have not been designed to cope with. The process of morphological tagging when applied to Hungarian data to produce corpora annotated at least at the morphosyntactic level is most indicative of this problem: several of the algorithms (either rule-based or statistical) that have been used very successfully in other domains cannot readily be applied to a language exhibiting such a varied morphology and huge number of wordforms as Hungarian. The paper will describe a robust tagging scenario for Hungarian using a relatively simple stochastic system augmented with external morphological processing, which can overcome the two most conspcicuous problems: the complexity of morphosyntactic descriptions and most importantly the huge number of possible wordforms.}, ANNOTE = {COLIURL : Oravecz:2002:ESP.pdf Oravecz:2002:ESP.ps} } @InProceedings{Pilzecker:2002, AUTHOR = {Pilzecker, Markus}, TITLE = {Semantically Driven Automatic Hyperlinking}, YEAR = {2002}, BOOKTITLE = {Proceedings of 15th European Conference on Artificial Intelligence (ECAI 2002), Workshop 22: Semantic Authoring, Annotation and Knowledge Markup, July 22}, PAGES = {99-102}, EDITOR = {Handschuh, Siegfried and Collier, Nigel and Dieng, Rose and Staab, Steffen}, ADDRESS = {Lyon, France}, URL = {http://www.dfki.de/~mp/document/publications/ecai_w22.ps.gz}, ABSTRACT = {This paper sketches some experiences and ideas, how a contemporary automatic hyperlinking system may be advantageously combined with sufficiently powerful methods that extract semantics from human language text.}, ANNOTE = {COLIURL : Pilzecker:2002:SDA.pdf Pilzecker:2002:SDA.ps} } @TechReport{Piskorski:2002, AUTHOR = {Piskorski, Jakub}, TITLE = {Finite-State Machine Toolkit}, YEAR = {2002}, NUMBER = {RR-02-04}, ADDRESS = {Saarbrücken}, TYPE = {Technical Report}, INSTITUTION = {DFKI}, URL = {http://www.dfki.de/dfkibib/publications/docs/Piskorski_2002_DFSMTK.pdf}, ABSTRACT = {Finite-state devices such as finite-state automata and finite-state transducers have been known since the emergence of computer science and are recently extensively used in many areas of language technology. The use of finite-state devices is mainly motivated by their time and space efficiency. In this paper we present the Finite-State Machine Toolkit for building, combining and optimizing the finite-state machines, developed at the Language Technology Lab of the German Research Cener for Artficial Intelligence.}, ANNOTE = {COLIURL : Piskorski:2002:FSM.pdf} } @InProceedings{Piskorski_et_al:2002, AUTHOR = {Piskorski, Jakub and Drozdzynski, Witold and Xu, Feiyu and Scherf, Oliver}, TITLE = {A Flexible XML-based Regular Compiler for Creation and Converting Linguistic Resources}, YEAR = {2002}, BOOKTITLE = {Proceedings of the 3rd International Conference on Language Resources an Evaluation (LREC'02)}, ADDRESS = {Las Palmas, Canary Islands, Spain}, URL = {http://www.dfki.de/~feiyu/regular_compiler.pdf}, ABSTRACT = {Finite-state devices are widely used to compactly model linguistic phenomena, whereas regular expressions are regarded as the adequate level of abstraction for thinking about finite-state languages. In this paper we present a flexible XML-based and Unicode-compatible regular compiler for creating, and integrating existing linguistic resources. Our tool provides user-friendly graphical interface which enables the transparent control of the compilation process and allows for testing generated finite-state grammars with several diagnostic tools. Through the direct database connection, existing linguistic resources can be converted into user-definable finite-state representations.}, ANNOTE = {COLIURL : Piskorski:2002:FXB.pdf} } @InProceedings{Piskorski_et_al:2002_1, AUTHOR = {Piskorski, Jakub and Jaeger, Tilman and Xu, Feiyu}, TITLE = {A Framework for Domain and Task Adaptive Named-Entity Recognition}, YEAR = {2002}, BOOKTITLE = {Proceedings of the 5th International Baltic Conference on Databases and Information Systems, June 3-6}, ADDRESS = {Tallinn, Estonia}, URL = {http://www.dfki.de/~feiyu/balt.tar.gz}, ABSTRACT = {Robust Named--Entity Recognition software is an essential preprocessing tool for performing more complex text processing tasks in business information systems. In this paper we present a Framework for Domain and Task Adaptive Named--Entity Recognition. It consists of several clear--cut subcomponents which can be flexibly and variably combined together in order to construct a task--specific NE--Recognition tool. Additionally, a diagnostic tool for automatic prediction of best system configuration is provided, which speeds up the development cycle.}, ANNOTE = {COLIURL : Piskorski:2002:FDT.tar} } @InProceedings{Piwek_et_al:2002, AUTHOR = {Piwek, Paul and Krenn, Brigitte and Schröder, Marc and Grice, Martine and Baumann, Stefan and Pirker, Hannes}, TITLE = {RRL: A Rich Represenatation Language for the Description of Agent Behaviour in NECA}, YEAR = {2002}, BOOKTITLE = {Proceedings of AAMAS 2002 Workshop:Embodied Conversational Agents - Let's Specify and Evaluate Them!, July 15-16}, ADDRESS = {Bologna, Italy}, URL = {http://www.vhml.org/workshops/AAMAS/papers/piwek.pdf}, ABSTRACT = {In this paper, we describe the Rich Representation Language (RRL) which is used in the NECA system. The NECA system generates interactions between two or more animated characters. The RRL is a formal framework for representing the information that is exchanged at the interfaces between the various NECA system modules.}, ANNOTE = {COLIURL : Piwek:2002:RRR.pdf} } @PhdThesis{Prescher:2002, AUTHOR = {Prescher, Detlef}, TITLE = {EM-basierte maschinelle Lernverfahren für natürliche Sprachen}, YEAR = {2002}, NUMBER = {8(1)}, SERIES = {AIMS Report}, ADDRESS = {Stuttgart}, SCHOOL = {Universität Stuttgart, Institut für Maschinelle Sprachverarbeitung (IMS)}, URL = {http://www.dfki.de/~prescher/papers/bib/2002phd.prescher.pdf}, ABSTRACT = {This thesis presents the Expectation-Maximization algorithm (EM algorithm, Dempster et al. (1977)) in its practical and theoretical aspects. The EM algorithm is the stochastic basis of many machine learning algorithms for natural language processing. In the theoretical part of this thesis the stochastic basis of linguistics and the formal basis of the EM algorithm is explained. The practical part of this thesis presents a probabilistic clustering method for multivariate linguistic data and stochastic modeling of lexicalized grammars.}, ANNOTE = {COLIURL : Prescher:2002:EBM.pdf} } @Article{Pützer_Barry:2002, AUTHOR = {Pützer, Manfred and Barry, William J.}, TITLE = {Differential Weighting of Phonetic Properties in Cross-Dialectal Perception}, YEAR = {2002}, JOURNAL = {PHONUS}, VOLUME = {6, Festschrift für Max Mangold}, PAGES = {191-220} } @Article{Pützer_Barry:2002_1, AUTHOR = {Pützer, Manfred and Barry, William J.}, TITLE = {Methodische Aspekte der auditiven Bewertung von Stimmqualität}, YEAR = {2002}, JOURNAL = {Sprache Stimme Gehör}, NOTE = {to appear} } @Article{Pützer_et_al:2002, AUTHOR = {Pützer, Manfred and Moringlane, Jean Richard and Fuss, Gerhard}, TITLE = {Auswirkungen neurstimulatorischer Eingriffe auf das glottale Schwingungsverhalten bei Patienten mit M. Parkinson und Multipler Sklerose}, YEAR = {2002}, JOURNAL = {Folia Phoniatr. Logop.}, NOTE = {to appear} } @InProceedings{Raileanu_et_al:2002, AUTHOR = {Raileanu, Diana and Buitelaar, Paul and Vintar, Spela and Bay, Jörg}, TITLE = {Evaluation Corpora for Sense Disambiguation in the Medical Domain}, YEAR = {2002}, BOOKTITLE = {Proceedings of the 3rd International Conference on Language Resources and Evaluation (LREC'02), May 29-31}, ADDRESS = {Las Palmas, Canary Islands, Spain}, URL = {http://dfki.de/~paulb/lrec2002.eval.ps http://www.dfki.de/dfkibib/publications/docs/lrec2002.eval.final.pdf http://www2.arnes.si/~svinta/lrec2002.eval.final.pdf}, ABSTRACT = {An important aspect of word sense disambiguation is the evaluation of different methods and parameters. Unfortunately, there is a lack of test sets for evaluation, specifically for languages other than English and even more so for specific domains like medicine. Given that our work focuses on English as well as German text in the medical domain, we had to develop our own evaluation corpora in order to test our disambiguation methods. In this paper we describe the work on developing these corpora, using GermaNet and UMLS as (lexical) semantic resources, next to a description of the annotation tool KiC that we developed for support of the annotation task.}, ANNOTE = {COLIURL : Raileanu:2002:ECS.pdf Raileanu:2002:ECS.ps} } @InProceedings{Ripplinger_et_al:2002, AUTHOR = {Ripplinger, Bärbel and Vintar, Spela and Buitelaar, Paul}, TITLE = {Cross-Lingual Information Retrieval through Semantic Annotation}, YEAR = {2002}, BOOKTITLE = {Proceedings of the Workshop on Natural Language Processing in Biomedical Applications (NLPBA'02), March 8-9}, ADDRESS = {Nicosia, Cyprus}, URL = {http://dfki.de/~paulb/nlpba.ps}, ABSTRACT = {We present a framework for concept-based, cross-lingual information retrieval (CLIR) in the medical domain, which is under development in the MUCHMORE project. Our approach is based on using the Unified Medical Language System (UMLS) as the primary source of semantic data, whereby documents and queries are annotated with multiple layers of linguistic information. Linguistic processing includes POS-tagging, morphological analysis, phrase recognition and the identification of medical concepts and semantic relations between them. The paper describes experiments in mono- and bilingual document retrieval, performed on a parallel English-German corpus of medical abstracts. Results show on the one hand that linguistic processing, especially lemmatisation and compound analysis, is a crucial step to achieving good baseline performance. On the other hand we show that semantic information, specifically the combined use of concepts and relations, significantly increases performance in cross-lingual retrieval.}, ANNOTE = {COLIURL : Ripplinger:2002:CLI.pdf Ripplinger:2002:CLI.ps} } @InProceedings{Siegel_Bender:2002, AUTHOR = {Siegel, Melanie and Bender, Emily}, TITLE = {Efficient Deep Processing of Japanese}, YEAR = {2002}, BOOKTITLE = {Proceedings of the 3rd Workshop on Asian Language Resources and International Standardization. COLING 2002 Post-Conference Workshop, August 31}, ADDRESS = {Taipei, Taiwan}, URL = {http://arxiv.org/pdf/cs.CL/0207005.pdf}, ABSTRACT = {We present a broad coverage Japanese grammar written in the HPSG formalism with MRS semantics. The grammar is created for use in real world applications, such that robustness and performance issues play an important role. It is connected to a POS tagging and word segmentation tool. This grammar is being developed in a multilingual context, requiring MRS structures that are easily comparable across languages.}, ANNOTE = {COLIURL : Siegel:2002:EDP.pdf} } @Article{Sturt_et_al:2002, AUTHOR = {Sturt, Patrick and Scheepers, Christoph and Pickering, Martin J.}, TITLE = {Syntactic Ambiguity Resolution after Initial Misanalysis: The Role of Recency}, YEAR = {2002}, JOURNAL = {Journal of Memory and Language}, VOLUME = {46}, PAGES = {371-390} } @InProceedings{Tsovaltzi_Matheson:2002, AUTHOR = {Tsovaltzi, Dimitra and Matheson, Colin}, TITLE = {Formalising Hinting in Tutorial Dialogues}, YEAR = {2002}, BOOKTITLE = {6th workshop on the semantics and pragmatics of dialogue (EDILOG 2002), September 4-6}, PAGES = {185-192}, EDITOR = {Bos, Johan and Foster, Mary Ellen and Matheson, Colin}, ADDRESS = {University of Edinburgh, Scotland}, URL = {http://www.ltg.ed.ac.uk/edilog/papers/185.pdf}, ABSTRACT = {The formalisation of the hinting process in Tutorial Dialogues is undertaken in order to simulate the Socratic teaching method. An adaptation of the BE&E annotation scheme for Dialogue Moves, based on the theory of social obligations, is sketched, and a taxonomy of hints and a selection algorithm is suggested based on data from the BE&E corpus. Both the algorithm and the tutor's reasoning are formalised in the context of the information state theory of dialogue management developed on the trindi project. The algorithm is characterised using update rules which take into account the student model, and the tutor's reasoning process is described in terms of context accommodation.}, ANNOTE = {Tsovaltzi:2002:FHT} } @InProceedings{Uszkoreit:2002, AUTHOR = {Uszkoreit, Hans}, TITLE = {New Chances for Deep Linguistic Processing}, YEAR = {2002}, BOOKTITLE = {Proceedings of the 19th International Conference on Computational Linguistics (COLING'02), August 24 - September 1}, PUBLISHER = {Morgan Kauffmann Press}, ABSTRACT = {The Grammatical analysis with linguistically designed grammars has always been a central topic of investigation in theoretical computational linguistics. However, deep grammatical analysis has played a negligible role in the development of language technology applications. Deep parsers have been lacking efficiently and robustness. Building up coverage has been slow and costly. The few linguistic grammars that truly exhibit large coverage have caused a constant fight with extensive ambiguity. In my talk I will present recent developments that provide new challenges and opportunities for linguistic methods. Increased efficiency of deep parsing and the embedding of a selective deep analysis into a robust shallow regime for information extraction offer ways to employ deep parsing in an environment where it can improve results without ruining robustness. I will argue that such a selective utilization as we have realized it by an integration of HPSG parsing into a hybrid IE system comprised of statistical and FST components, also provides a promising direction for gradual, measurable controlled progress in the development of deep grammars and lexicons.} } @Article{Vasishth:2002, AUTHOR = {Vasishth, Shravan}, TITLE = {Word Order, Negation, and Negative Polarity in Hindi}, YEAR = {2002}, JOURNAL = {Journal of Language and Computation}, VOLUME = {3}, URL = {ftp://ftp.ling.ohio-state.edu/pub/Students/Vasishth/Published/JLAC2001/vasishth.pdf}, NOTE = {to appear}, ANNOTE = {COLIURL : Vasishth:2002:WON.pdf} } @MastersThesis{Vasishth:2002_1, AUTHOR = {Vasishth, Shravan}, TITLE = {An Abductive Inference Based Model of Human Sentence Parsing}, YEAR = {2002}, MONTH = {March}, ADDRESS = {Columbus}, SCHOOL = {Ohio State University, Department of Computer and Information Science}, URL = {ftp://ftp.ling.ohio-state.edu/pub/Students/Vasishth/MSThesis/msthesis.ps}, ANNOTE = {COLIURL : Vasishth:2002:AIB.pdf Vasishth:2002:AIB.ps} } @PhdThesis{Vasishth:2002_2, AUTHOR = {Vasishth, Shravan}, TITLE = {Working Memory in Sentence Comprehension: Processing Hindi Center Embeddings}, YEAR = {2002}, MONTH = {June}, ADDRESS = {Columbus}, SCHOOL = {Ohio State University, Department of Linguistics}, URL = {http://www.ling.ohio-state.edu/~vasishth/PhD/diss.pdf.gz http://www.ling.ohio-state.edu/~vasishth/PhD/diss.ps.gz}, NOTE = {To appear in the Garland series, Routledge Press, NY}, ANNOTE = {COLIURL : Vasishth:2002:WMS.pdf} } @InProceedings{Vasishth_Joseph:2002, AUTHOR = {Vasishth, Shravan and Joseph, Brian D.}, TITLE = {Constellations, Polysemy, and Hindi}, YEAR = {2002}, BOOKTITLE = {Berkeley Linguistics Society Conference (BLS 28), February 15-18}, ADDRESS = {University of California, Berkeley, USA}, URL = {ftp://ftp.ling.ohio-state.edu/pub/Students/Vasishth/Published/BLS2002/vasishth.ps} } @InProceedings{Vintar_et_al:2002, AUTHOR = {Vintar, Spela and Buitelaar, Paul and Ripplinger, Bärbel and Sacaleanu, Bogdan and Raileanu, Diana and Prescher, Detlef}, TITLE = {An Efficient and Flexible Format for Linguistic and Semantic Annotation}, YEAR = {2002}, BOOKTITLE = {Proceedings of the 3rd International Conference on Language Resources and Evaluation (LREC'02), May 29-31}, ADDRESS = {Las Palmas, Canary Islands, Spain}, URL = {http://dfki.de/~paulb/lrec2002.dtd.ps http://www.dfki.de/dfkibib/publications/docs/lrec2002.dtd.final.pdf}, ABSTRACT = {The paper describes an XML annotation format and tool developed within the MUCHMORE project. The annotation scheme was designed specifically for the purposes of Cross-Lingual Information Retrieval in the medical domain so as to allow both efficient and flexible access to layers of information. We use a parallel English-German corpus of medical abstracts and annotate it with linguistic information (tokenisation, part-of-speech tagging, lemmatisation and decomposition, phrase recognition, grammatical functions) as well as semantic information from various sources. The annotation of medical terms/concepts, semantic types and semantic relations is based on the Unified Medical Language System (UMLS). Additionally, we use EuroWordNet as a general-language resource in annotating word senses and to compare domain-specific and general language use. A major aim of the project is also to complement existing ontological resources by extracting new terms and new semantic relations. We present the annotation scheme, which is conceptually related to stand-off annotation, and describe our tool for automatic semantic annotation.}, ANNOTE = {COLIURL : Vintar:2002:EFF.pdf Vintar:2002:EFF.ps} } @Article{Volk_et_al:2002, AUTHOR = {Volk, Martin and Ripplinger, Bärbel and Vintar, Špela and Buitelaar, Paul and Raileanu, Diana and Sacaleanu, Bogdan}, TITLE = {Semantic Annotation for Concept-Based Cross-Language Medical Information Retrieval}, YEAR = {2002}, JOURNAL = {International Journal of Medical Informatics}, VOLUME = {67}, NUMBER = {1-3}, PAGES = {97-112}, URL = {http://dfki.de/~paulb/jmi.pdf}, ABSTRACT = {We present a framework for concept-based cross-language information retrieval in the medical domain, which is under development in the MUCHMORE project. Our approach is based on using the Unified Medical Language System (UMLS) as the primary source of semantic data. Documents and queries are annotated with multiple layers of linguistic information. Linguistic processing includes part-of-speech tagging, morphological analysis, phrase recognition and the identification of medical terms and semantic relations between them. The paper describes experiments in monolingual and cross-language document retrieval, performed on a corpus of medical abstracts. Results show that linguistic processing, especially lemmatization and compound analysis for German, is a crucial step in achieving a good baseline performance. On the other hand, they show that semantic information, specifically the combined use of concepts and relations, increases the performance in monolingual and cross-language retrieval.}, ANNOTE = {COLIURL : Volk:2002:SAC.pdf} } @Article{Wokurek_Pützer:2002, AUTHOR = {Wokurek, Wolfgang and Pützer, Manfred}, TITLE = {Akustische Analyse normalstimmlicher und pathologischer Phonation}, YEAR = {2002}, NOTE = {to appear} } @InProceedings{Xu_et_al:2002, AUTHOR = {Xu, Feiyu and Kurz, Daniela and Piskorski, Jakub and Schmeier, Sven}, TITLE = {Term Extraction and Mining Term Relations from Free-Text Documents in the Financial Domain}, YEAR = {2002}, BOOKTITLE = {Proceedings of the 5th International Conference on Business Information Systems (BIS'02), April 24-25}, ADDRESS = {Poznan, Poland}, URL = {http://www.dfki.de/~feiyu/Bis2002.pdf}, ABSTRACT = {In this paper, we present an approach to learning domain relevant terms automatically. We took the financial domain as our experiment domain.}, NOTE = {to appear}, ANNOTE = {COLIURL : Xu:2002:TEM.pdf} } @InProceedings{Xu_et_al:2002_1, AUTHOR = {Xu, Feiyu and Kurz, Daniela and Piskorski, Jakub and Schmeier, Sven}, TITLE = {A Domain Adaptive Approach to Automatic Acquisition of Domain Relevant Terms and their Relations with Bootstrapping}, YEAR = {2002}, BOOKTITLE = {Proceedings of the 3rd International Conference on Language Resources an Evaluation (LREC'02), May 29-31}, ADDRESS = {Las Palmas, Canary Islands, Spain}, URL = {http://www.dfki.uni-sb.de/~feiyu/LREC_TermExtraction_final.pdf}, ABSTRACT = {In this paper, we present an unsupervised hybrid text-mining approach to automatic acquisition of domain relevant terms and their relations. We deploy the TFIDF-based term classification method to acquire domain relevant single-word terms. Further, we apply two strategies in order to learn lexico-syntatic patterns which indicate paradigmatic and domain relevant syntagmatic relations between the extracted terms. The first one uses an existing ontology as initial knowledge for learning lexico-syntactic patterns, while the second is based on different collocation acquisition methods to deal with the free-word order languages like German. This domain-adaptive method yields good results even when trained on relatively small training corpora. It can be applied to different real-world applications, which need domain-relevant ontology, for example, information extraction, information retrieval or text classification.}, ANNOTE = {COLIURL : Xu:2002:DAA.pdf} } @InCollection{Egg:2002_2, AUTHOR = {Egg, Markus}, TITLE = {Beginning Novels and Finishing Hamburgers - Remarks on the Semantics of to begin}, YEAR = {2002}, BOOKTITLE = {Ereignisstrukturen}, VOLUME = {76}, EDITOR = {Dölling, Johannes and Zybatow, Tatjana}, SERIES = {Linguistische Arbeitsberichte}, ADDRESS = {Leipzig}, PUBLISHER = {Universität Leipzig}, ABSTRACT = {Verbs like begin may take either a VP or an NP complement, but their meaning is pretty similar in both cases, e.g., for begin, the start of an eventuality is at stake. Pustejovsky's approach captures this similarity in terms of an invariant meaning of the verb, which entails a process or reinterpretation for the transitive variant of the verb. I will show that while the intuitions of this proposal are on the right track, its actual implementation suffers from a number of shortcomings. I will offer an analysis that preserves Pustejovsky's intuition but avoids these shortcomings. My analysis is based on an appropriate underspecifcation formalism.} } @Article{Hansen_et_al:2002, AUTHOR = {Hansen, Silvia and Klaumann, Mary and Neumann, Stella}, TITLE = {How to overcome registerial translation problems}, YEAR = {2002}, JOURNAL = {Revista Brasileira de Linguistica Aplicada}, VOLUME = {2}, NUMBER = {2}, PAGES = {15-23} } @InCollection{Kruijff-Korbayova_et_al:2002_2, AUTHOR = {Kruijff-Korbayova, Ivana and Bateman, John and Kruijff, Geert-Jan M.}, TITLE = {Generation of Contextually Appropriate Word Order}, YEAR = {2002}, BOOKTITLE = {Information Sharing}, PAGES = {193-222}, EDITOR = {van Deemter, Kees and Kibble, Rodger}, PUBLISHER = {CSLI} } @InProceedings{Warner_Weber:2002, AUTHOR = {Warner, Natasha and Weber, Andrea}, TITLE = {Stop epenthesis at syllable boundaries.}, YEAR = {2002}, BOOKTITLE = {Proceedings of the 7th International Conference on Spoken Language Processing}, PAGES = {1121-1124}, ADDRESS = {Adam's Mark Hotel, Denver, Colorado} } @Article{Weber:2002, AUTHOR = {Weber, Andrea}, TITLE = {Assimilation violation and spoken-language processing: A supplementary report.}, YEAR = {2002}, JOURNAL = {Language and Speech}, VOLUME = {45}, PAGES = {37-46} } @PhdThesis{Erk:2002, AUTHOR = {Erk, Katrin}, TITLE = {Parallelism Constraints in Underspecified Semantics}, YEAR = {2002}, MONTH = {December}, SCHOOL = {Saarland University}, URL = {http://www.ps.uni-sb.de/Papers/abstracts/disserk.html} } @InCollection{Kruijff:2002, AUTHOR = {Kruijff, Geert-Jan M.}, TITLE = {Formulating a category of informativity}, YEAR = {2002}, BOOKTITLE = {Information Structure in a Cross-Linguistic Perspective}, PAGES = {129-146}, EDITOR = {Hasselgard, Hilde and Johansson, Stig and Behrens, Bergljot and Fabricius-Hansen, Cathrine}, ADDRESS = {Amsterdam New York}, PUBLISHER = {Rodopi} } @InProceedings{Oepen_et_al:2002_1, AUTHOR = {Oepen, Stephan and Bender, Emily and Callmeier, Uli and Flickinger, Dan and Siegel, Melanie}, TITLE = {Parallel Distributed Grammar Engineering for Practical Applications.}, YEAR = {2002}, BOOKTITLE = {Proceedings of the 19th International Conference on Computational Linguistics}, ADDRESS = {Taipei, Taiwan}, ANNOTE = {HOMEPAGE : http://www.dfki.de/~siegel/mypubs.html} } @MastersThesis{Vasishth:2002_3, AUTHOR = {Vasishth, Shravan}, TITLE = {An Abductive Inference Based Model of Human Sentence Parsing}, YEAR = {2002}, ADDRESS = {Columbus, OH}, SCHOOL = {Computer and Information Science, Ohio State University} } @InProceedings{Vasishth:2002_4, AUTHOR = {Vasishth, Shravan}, TITLE = {Distance effects or similarity-based interference?: A model comparison perspective}, YEAR = {2002}, BOOKTITLE = {Proceedings of Architectures and Mechanisms for Language Processing conference}, PAGES = {Vasishth:2002:DES}, ADDRESS = {Tenerife, Canary Islands, Spain} } @InBook{Andreeva_Barry:2002, AUTHOR = {Andreeva, Bistra and Barry, William J.}, TITLE = {Current Approaches in Formal Slavic Linguistics}, YEAR = {2002}, PAGES = {139-147}, EDITOR = {Kosta, Peter and Frasek, Jens}, PUBLISHER = {Peter Lang}, CHAPTER = {Intonation von Checks in der Sofia-Varietät des Bulgarischen} } @InProceedings{Ourioupina:2002, AUTHOR = {Ourioupina, Olga}, TITLE = {Extracting Geographical Knowledge from the Internet}, YEAR = {2002}, BOOKTITLE = {Proceedings of the ICDM-AM International Workshop on Active Mining 2002}, ADDRESS = {Ourioupina:2002:EGK} } @InProceedings{Yao_et_al:2002, AUTHOR = {Yao, Tianfang and Ding, W. and Erbach, Gregor}, TITLE = {Correcting word segmentation and part-of-speech tagging errors for Chinese named entity recognition}, YEAR = {2002}, BOOKTITLE = {The Internet Challenge: Technology and Applications}, PAGES = {29-36}, EDITOR = {Hommel, Günter and Huanye, Shen}, ADDRESS = {Dordrecht}, PUBLISHER = {Kluwer Academic Publishers} } @InProceedings{Yao_et_al:2002_1, AUTHOR = {Yao, Tianfang and Ding, W. and Erbach, Gregor}, TITLE = {Repairing Errors for Chinese Word Segmentation and Part-of-speech Tagging}, YEAR = {2002}, BOOKTITLE = {Proceedings of the First International Conference on Machine Learning and Cybernetics 2002 (ICMLC 2002)}, PAGES = {1881-1886}, ADDRESS = {Beijing}, PUBLISHER = {Yao:2002:RECa} } @Book{Woirgardt-Kobayashi:2002, AUTHOR = {Woirgardt-Kobayashi, Ryuko}, TITLE = {Enjoksai: Schülerinnenprostitution in Japan - Gewalt oder Emanzipation? Ein Beitrag zur Geschlechterforschung}, YEAR = {2002} } @PhdThesis{Avgustinova:2002_2, AUTHOR = {Avgustinova, Tania}, TITLE = {Shared Grammatical Resources for Slavic Languages. Selected topic in multilingual grammar design with special reference to Slavic morphosyntax}, YEAR = {2002}, ADDRESS = {Saarbrücken}, SCHOOL = {Universität des Saarlandes}, TYPE = {Habilitationsschrift} } @Misc{Paris:2002, AUTHOR = {Paris, Garance}, TITLE = {Interaction between tag set design and multilingual information extraction}, YEAR = {2002}, ADDRESS = {Saarbrücken, Germany}, SCHOOL = {Computerlinguistik, Universität des Saarlandes}, TYPE = {Bachelor's thesis} } @InProceedings{Kordoni:2002_2, AUTHOR = {Kordoni, Valia}, TITLE = {Derivational vs. Nonderivational Linguistic Models in the 20th and 21st Centuries}, YEAR = {2002}, MONTH = {21 May}, BOOKTITLE = {Proceedings of the International Linguistics Conference Reviewing Linguistic Thought: Perspectives into the 21st Century}, ADDRESS = {Department of Language and Linguistics, Faculty of English Studies, School of Philosophy}, ORGANIZATION = {National and Kapodistrian University of Athens}, URL = {Kordoni:2002:DVN} } @MastersThesis{Brockmann:2002, AUTHOR = {Brockmann, Carsten}, TITLE = {Evaluating and Combining Approaches to Selectional Preference}, YEAR = {2002}, ADDRESS = {Saarbrücken, Saarland}, SCHOOL = {Computerlinguistik, Universität des Saarlandes}, TYPE = {Diplomarbeit} } @MastersThesis{Burchardt_Stephan:2002, AUTHOR = {Burchardt, Aljoscha and Stephan, Walter}, TITLE = {BuGS: Tableau Machine for Language Understanding}, YEAR = {2002}, ADDRESS = {Im Stadtwald, 66123 Saarbrücken, Saarland}, SCHOOL = {Computerlinguistik, Universität des Saarlandes}, TYPE = {Diplomarbeit} } @MastersThesis{Crispi:2002, AUTHOR = {Crispi, Claudia}, TITLE = {Linguistische Fragmentkombination und Annotation auf der Basis von Chunk-Parsing}, YEAR = {2002}, ADDRESS = {Im Stadtwald, 66123 Saarbrücken, Saarland}, SCHOOL = {Computerlinguistik, Universität des Saarlandes}, TYPE = {Diplomarbeit} } @MastersThesis{Jäger:2002, AUTHOR = {Jäger, Tilman}, TITLE = {AntEx: Ein diagnostizierbares, domänenadaptives Eigennamenerkennungssystem}, YEAR = {2002}, ADDRESS = {Saarbrücken, Germany}, SCHOOL = {Computerlinguistik, Universität des Saarlandes}, TYPE = {Diplomarbeit} } @MastersThesis{Klöckner:2002, AUTHOR = {Klöckner, Kerstin}, TITLE = {Arbeitsgedächtnis oder Erfahrenheit: Experimentelle Evidenzen und ihre netzwerkbasierte Simulation zu deutschen Subjekt- und Objektrelativsätzen}, YEAR = {2002}, ADDRESS = {Saarbrücken, Germany}, SCHOOL = {Computerlinguistik, Universität des Saarlandes}, TYPE = {Diplomarbeit} } @MastersThesis{Korthals:2002, AUTHOR = {Korthals, Christian}, TITLE = {Unsupervised Learning of Word Order Rules}, YEAR = {2002}, ADDRESS = {Saarbrücken, Germany}, SCHOOL = {Computerlinguistik, Universität des Saarlandes}, TYPE = {Diplomarbeit} } @MastersThesis{Pfleger:2002, AUTHOR = {Pfleger, Norbert}, TITLE = {Discourse Processing for Multimodal Dialogues and its Application in SmartKom}, YEAR = {2002}, ADDRESS = {Saarbrücken, Germany}, SCHOOL = {Computerlinguistik, Universität des Saarlandes}, TYPE = {Diplomarbeit} } @MastersThesis{Raileanu:2002, AUTHOR = {Raileanu, Diana}, TITLE = {Semantic Tagging of Medical Texts with GermaNet}, YEAR = {2002}, ADDRESS = {Saarbrücken, Germany}, SCHOOL = {Computerlinguistik, Universität des Saarlandes}, TYPE = {Diplomarbeit} } @MastersThesis{Rinck:2002, AUTHOR = {Rinck, Matthias}, TITLE = {Ein Metaregelformalismus für TG/2}, YEAR = {2002}, ADDRESS = {Saarbrücken, Germany}, SCHOOL = {Computerlinguistik, Universität des Saarlandes}, TYPE = {Diplomarbeit} } @MastersThesis{Sauer:2002, AUTHOR = {Sauer, Joachim}, TITLE = {Textsorten-adaptives Template-Merging - Steigerung der Performanz durch Anaphern-Resolution}, YEAR = {2002}, ADDRESS = {Saarbrücken, Germany}, SCHOOL = {Computerlinguistik, Universität des Saarlandes}, TYPE = {Diplomarbeit} } @MastersThesis{Stenzhorn:2002, AUTHOR = {Stenzhorn, Holger}, TITLE = {XtraGen. A Natural Language Generation System Using Java and XML Technologies}, YEAR = {2002}, ADDRESS = {Saarbrücken, Germany}, SCHOOL = {Computerlinguistik, Universität des Saarlandes}, TYPE = {Diplomarbeit} } @Proceedings{Wei Ding_Gregor:2002, TITLE = {Repairing Errors for Chinese Word Segmentation and Part-of-Speech Tagging}, YEAR = {2002}, MONTH = {November}, VOLUME = {Proc. of the First International Conference on Machine Learning and Cybernetics 2002 (ICMLC 2002)}, EDITOR = {Tianfang Yao, Wei Ding and Erbach, Gregor}, ADDRESS = {Beijing, China}, PUBLISHER = {IEEE and Hebei University} } @Proceedings{Wei Ding_Gregor:2002_1, TITLE = {Correcting Word Segmentation and Part-Of-Speech Tagging Errors for Chinese Named Entity Recognition}, YEAR = {2002}, MONTH = {October}, VOLUME = {In Günter Hommel and Sheng Huanye (Eds.): The Internet Challenge: Technology and Applications}, EDITOR = {Tianfang Yao, Wei Ding and Erbach, Gregor}, ADDRESS = {Dordrecht, The Netherlands}, PUBLISHER = {Kluwer Academic Publishers} } @InProceedings{Zheng_et_al:2002, AUTHOR = {Zheng, Zhiping and Huang, Huiyan and Schmeier, Sven}, TITLE = {Deploying Web-based Question Answering System to Local Archive}, YEAR = {2002}, BOOKTITLE = {Fifth International Conference on TEXT, SPEECH and DIALOGUE (TSD 2002)}, ADDRESS = {Brno, Czech Republic.}, PUBLISHER = {Zheng:2002:DWB} } @InProceedings{Zheng_Gregor:2002, AUTHOR = {Zheng, Zhiping and Gregor, Erbach.}, TITLE = {Specialized search in linguistics and languages.}, YEAR = {2002}, BOOKTITLE = {XI International Conference on Computing (CIC 2002).}, ADDRESS = {Mexico City, Mexico.} } @InProceedings{Crocker:2002, AUTHOR = {Crocker, Matthew W.}, TITLE = {Parsing as Prediction: Evidence from SVO and OVS constructions in German}, YEAR = {2002}, BOOKTITLE = {The 6th Konferenz zur Verarbeitung natürlicher Sprache (KONVENS 2002)}, PAGES = {3-6}, ADDRESS = {Saarbrücken, Germany} } @InProceedings{Crocker:2002_1, AUTHOR = {Crocker, Matthew W.}, TITLE = {Expectations in incremental language comprehension: The role of context and experience}, YEAR = {2002}, BOOKTITLE = {The European Society of Philosophy and Psychology (ESPP-2002)}, ADDRESS = {Lyon, France} } @InProceedings{Hadelich_et_al:2002, AUTHOR = {Hadelich, Kerstin and Crocker, Matthew W. and Scheepers, Christoph}, TITLE = {Powerful pictures: Priming planning or production or both? (poster)}, YEAR = {2002}, BOOKTITLE = {AMLaP-2002}, ADDRESS = {Tenerife, Spain} } @InProceedings{Kamide_et_al:2002, AUTHOR = {Kamide, Yuki and Scheepers, Christoph and Altmann, Gerry and Crocker, Matthew W.}, TITLE = {Integration of syntactic and semantic information in predictive processing: Anticipatory eye-movements in German sentence processing}, YEAR = {2002}, BOOKTITLE = {The Annual CUNY Conference on Sentence Processing}, ADDRESS = {New York, NY} } @Article{Keller_Asudeh:2002, AUTHOR = {Keller, Frank and Asudeh, Ash}, TITLE = {Probabilistic Learning Algorithms and Optimality Theory}, YEAR = {2002}, JOURNAL = {Linguistic Inquiry}, VOLUME = {33}, NUMBER = {2}, PAGES = {225-244} } @InProceedings{Keller_et_al:2002_1, AUTHOR = {Keller, Frank and Scheepers, Christoph and Becker, S. and Foeldesi, C.}, TITLE = {Context effects on verb frame bias}, YEAR = {2002}, BOOKTITLE = {The 8th Annual Conference on Architectures and Mechanisms for Language Processing (AMLaP-2002)}, ADDRESS = {Tenerife, Spain} } @InProceedings{Knoeferle_et_al:2002, AUTHOR = {Knoeferle, Pia and Crocker, Matthew W. and Scheepers, Christoph}, TITLE = {Anticipatory eye movements in initially ambiguous sentences}, YEAR = {2002}, BOOKTITLE = {AMLaP-2002}, ADDRESS = {Tenerife, Spain} } @InProceedings{Melinger_Kita:2002 (in press), AUTHOR = {Melinger, Alissa and Kita, Sotaro}, TITLE = {Does gesture help processes of speech production?: Evidence for conceptual level facilitation}, YEAR = {2002}, BOOKTITLE = {The Berkeley Linguistics Society Annual Meeting}, ADDRESS = {Berkeley, USA} } @InProceedings{Muckel_et_al:2002, AUTHOR = {Muckel, Sandra and Scheepers, Christoph and Crocker, Matthew W.}, TITLE = {Anticipating German particle verb meanings: Effects of lexical frequency and plausibility}, YEAR = {2002}, BOOKTITLE = {AMLaP-2002}, ADDRESS = {Tenerife, Spain} } @InProceedings{Scheepers_Crocker:2002, AUTHOR = {Scheepers, Christoph and Crocker, Matthew W.}, TITLE = {Constituent order priming from reading to listening}, YEAR = {2002}, BOOKTITLE = {AMLaP-2002}, ADDRESS = {Tenerife, Spain} } @InProceedings{Abramowicz_Piskorski:2002_1, AUTHOR = {Abramowicz, Witold and Piskorski, Jakub}, TITLE = {Information Extraction from Free Text Business Documents}, YEAR = {2002}, BOOKTITLE = {Proceedings of IRMA - Information Resources Management Association International Conference, May 19-22}, ADDRESS = {Seattle}, ABSTRACT = {One of the most difficult aspects of using search technology is the process of getting information in shape for searching. The objective of this paper is an investigation of the applicability of information extraction techniques in real-world business applications dealing with textual data since business relevant data is mainly transmitted through free-text documents. Further, we demonstrate an enormous indexing potential of lightweight linguistic text processing techniques applied in information extraction systems in other closely related fields of information technology which concern processing vast amounts of textual data.} } @InProceedings{Albrecht_et_al:2002_1, AUTHOR = {Albrecht, Irene and Haber, Jörg and Kähler, Kolja and Schröder, Marc and Seidel, Hans-Peter}, TITLE = {May I talk to you? :-) - Facial Animation from Text}, YEAR = {2002}, BOOKTITLE = {Proceedings of the 10th Pacific Conference on Computer Graphics and Applications (Pacific Graphics 2002), October 9-11}, EDITOR = {Coquillart, Sabine and Shum, Heung-Yeung and Hu, Shi-Min}, ADDRESS = {Tsinghua University, Beijing}, URL = {http://www.mpi-sb.mpg.de/resources/FAM/publ/pg2002.pdf}, ABSTRACT = {We introduce a facial animation system that produces real-time animation sequences including speech synchronization and non-verbal speech-related facial expressions from plain text input. A state-of-the-art text-to-speech synthesis component performs linguistic analysis of the text input and creates a speech signal from phonetic and intonation information. The phonetic transcription is additionally used to drive a speech synchronization method for the physically based facial animation. Further high-level information from the linguistic analysis such as different types of accents or pauses as well as the type of the sentence is used to generate non-verbal speech-related facial expressions such as movement of head, eyes, and eyebrows or voluntary eye blinks. Moreover, emoticons are translated into XML markup that triggers emotional facial expressions.}, ANNOTE = {COLIURL : Albrecht:2002:FAT.pdf} } @InProceedings{Abramowicz_Piskorski:2002_2, AUTHOR = {Abramowicz, Witold and Piskorski, Jakub}, TITLE = {Information Extraction from Free Text Business Documents}, YEAR = {2002}, BOOKTITLE = {Proceedings of IRMA - Information Resources Management Association International Conference, May 19-22}, ADDRESS = {Seattle}, ABSTRACT = {One of the most difficult aspects of using search technology is the process of getting information in shape for searching. The objective of this paper is an investigation of the applicability of information extraction techniques in real-world business applications dealing with textual data since business relevant data is mainly transmitted through free-text documents. Further, we demonstrate an enormous indexing potential of lightweight linguistic text processing techniques applied in information extraction systems in other closely related fields of information technology which concern processing vast amounts of textual data.} } @InProceedings{Albrecht_et_al:2002_2, AUTHOR = {Albrecht, Irene and Haber, Jörg and Kähler, Kolja and Schröder, Marc and Seidel, Hans-Peter}, TITLE = {May I talk to you? :-) - Facial Animation from Text}, YEAR = {2002}, BOOKTITLE = {Proceedings of the 10th Pacific Conference on Computer Graphics and Applications (Pacific Graphics 2002), October 9-11}, EDITOR = {Coquillart, Sabine and Shum, Heung-Yeung and Hu, Shi-Min}, ADDRESS = {Tsinghua University, Beijing}, URL = {http://www.mpi-sb.mpg.de/resources/FAM/publ/pg2002.pdf}, ABSTRACT = {We introduce a facial animation system that produces real-time animation sequences including speech synchronization and non-verbal speech-related facial expressions from plain text input. A state-of-the-art text-to-speech synthesis component performs linguistic analysis of the text input and creates a speech signal from phonetic and intonation information. The phonetic transcription is additionally used to drive a speech synchronization method for the physically based facial animation. Further high-level information from the linguistic analysis such as different types of accents or pauses as well as the type of the sentence is used to generate non-verbal speech-related facial expressions such as movement of head, eyes, and eyebrows or voluntary eye blinks. Moreover, emoticons are translated into XML markup that triggers emotional facial expressions.}, ANNOTE = {COLIURL : Albrecht:2002:FAT.pdf} } @InProceedings{Abramowicz_Piskorski:2002_3, AUTHOR = {Abramowicz, Witold and Piskorski, Jakub}, TITLE = {Information Extraction from Free Text Business Documents}, YEAR = {2002}, BOOKTITLE = {Proceedings of IRMA - Information Resources Management Association International Conference, May 19-22}, ADDRESS = {Seattle}, ABSTRACT = {One of the most difficult aspects of using search technology is the process of getting information in shape for searching. The objective of this paper is an investigation of the applicability of information extraction techniques in real-world business applications dealing with textual data since business relevant data is mainly transmitted through free-text documents. Further, we demonstrate an enormous indexing potential of lightweight linguistic text processing techniques applied in information extraction systems in other closely related fields of information technology which concern processing vast amounts of textual data.} } @InProceedings{Albrecht_et_al:2002_3, AUTHOR = {Albrecht, Irene and Haber, Jörg and Kähler, Kolja and Schröder, Marc and Seidel, Hans-Peter}, TITLE = {May I talk to you? :-) - Facial Animation from Text}, YEAR = {2002}, BOOKTITLE = {Proceedings of the 10th Pacific Conference on Computer Graphics and Applications (Pacific Graphics 2002), October 9-11}, EDITOR = {Coquillart, Sabine and Shum, Heung-Yeung and Hu, Shi-Min}, ADDRESS = {Tsinghua University, Beijing}, URL = {http://www.mpi-sb.mpg.de/resources/FAM/publ/pg2002.pdf}, ABSTRACT = {We introduce a facial animation system that produces real-time animation sequences including speech synchronization and non-verbal speech-related facial expressions from plain text input. A state-of-the-art text-to-speech synthesis component performs linguistic analysis of the text input and creates a speech signal from phonetic and intonation information. The phonetic transcription is additionally used to drive a speech synchronization method for the physically based facial animation. Further high-level information from the linguistic analysis such as different types of accents or pauses as well as the type of the sentence is used to generate non-verbal speech-related facial expressions such as movement of head, eyes, and eyebrows or voluntary eye blinks. Moreover, emoticons are translated into XML markup that triggers emotional facial expressions.}, ANNOTE = {COLIURL : Albrecht:2002:FAT.pdf} } @InProceedings{Abramowicz_Piskorski:2002_4, AUTHOR = {Abramowicz, Witold and Piskorski, Jakub}, TITLE = {Information Extraction from Free Text Business Documents}, YEAR = {2002}, BOOKTITLE = {Proceedings of IRMA - Information Resources Management Association International Conference, May 19-22}, ADDRESS = {Seattle}, ABSTRACT = {One of the most difficult aspects of using search technology is the process of getting information in shape for searching. The objective of this paper is an investigation of the applicability of information extraction techniques in real-world business applications dealing with textual data since business relevant data is mainly transmitted through free-text documents. Further, we demonstrate an enormous indexing potential of lightweight linguistic text processing techniques applied in information extraction systems in other closely related fields of information technology which concern processing vast amounts of textual data.} } @InProceedings{Albrecht_et_al:2002_4, AUTHOR = {Albrecht, Irene and Haber, Jörg and Kähler, Kolja and Schröder, Marc and Seidel, Hans-Peter}, TITLE = {May I talk to you? :-) - Facial Animation from Text}, YEAR = {2002}, BOOKTITLE = {Proceedings of the 10th Pacific Conference on Computer Graphics and Applications (Pacific Graphics 2002), October 9-11}, EDITOR = {Coquillart, Sabine and Shum, Heung-Yeung and Hu, Shi-Min}, ADDRESS = {Tsinghua University, Beijing}, URL = {http://www.mpi-sb.mpg.de/resources/FAM/publ/pg2002.pdf}, ABSTRACT = {We introduce a facial animation system that produces real-time animation sequences including speech synchronization and non-verbal speech-related facial expressions from plain text input. A state-of-the-art text-to-speech synthesis component performs linguistic analysis of the text input and creates a speech signal from phonetic and intonation information. The phonetic transcription is additionally used to drive a speech synchronization method for the physically based facial animation. Further high-level information from the linguistic analysis such as different types of accents or pauses as well as the type of the sentence is used to generate non-verbal speech-related facial expressions such as movement of head, eyes, and eyebrows or voluntary eye blinks. Moreover, emoticons are translated into XML markup that triggers emotional facial expressions.}, ANNOTE = {COLIURL : Albrecht:2002:FAT.pdf} } @Article{barryrusso2002, AUTHOR = {Barry, John W. and Russo, Michela}, TITLE = {Gradi di elisione dello scha finale nelle variatà di Ischia e Pozzuoli: Unánalisi strumentale e implicazione ritmiche}, YEAR = {2002}, JOURNAL = {Quaderni Linguistici e Filologici XV. La fonetica acustica come strumento di analisi della variazione linguistica in Italia}, VOLUME = {Atti delle XII Giornate die Studio del Gruppo di Fonetica} }