@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}
}
|
