Computational Linguistics & Phonetics Computational Linguistics & Phonetics Fachrichtung 4.7 Universität des Saarlandes

Computational Linguistics Colloquium

Thursday, 21 February, 16:15
Conference Room, Building C7 4

Semantic role labeling of Spanish

Roser Morante
Tilburg University

In this talk I present several semantic role labelers of Spanish developed for the project "Semi-automatic techniques for semantic role labeling applied to a Spanish corpus" financed by the Spanish Ministry of Education. Semantic role labeling is a sentence-level natural-language processing task in which semantic roles are assigned to all arguments of a predicate. Given a sentence like (1), the system has to predict that "Saarland University, the first to be established after the Second World War," is the patient of "was founded", "in November 1948" is the temporal argument, and "with the support of the French Government and under the auspices of the University of Nancy" is the manner argument.

(1) Saarland University, the first to be established after the Second World War, was founded in November 1948 with the support of the French Government and under the auspices of the University of Nancy.

The main components of the systems that I present are memory-based classifiers. Memory-based language processing (Daelemans and Van den Bosch 2005) is based on the idea that NLP problems can be solved by storing annotated examples of the problem in their literal form in memory, and applying similarity-based reasoning on these examples in order two solve new ones.

The systems differ in the type of information that they process: constituent syntax versus dependency syntax, gold standard syntax versus predicted syntax, syntax versus no syntax at all. I will describe the systems, compare their results, and discuss their limitations.

W. Daelemans and A. Van den Bosch (2005) Memory-based language processing. Cambridge, UK: Cambridge University Press.

If you would like to meet with the speaker, please contact Caroline Sporleder.