RACAI: Meaning Affinity Models

Proceedings of the 4th International Workshop on Semantic Evaluations (SemEval-2007), pages 282–287, Prague, June 2007. c⃝2007 Association for Computational Linguistics RACAI: Meaning Affinity Models Radu Ion Institute for Artificial Intelligence 13, “13 Septembrie”, 050711, Bucharest 5, Romania radu@racai.ro Dan Tufis¸ Institute for Artificial Intelligence 13, “13 Septembrie”, 050711, Bucharest 5, Romania tufis@racai.ro Abstract This article introduces an unsupervised word sense disambiguation algorithm that is in- spired by the lexical attraction models of Yuret (1998). It is based on the assump- tion that the meanings of the words that form a sentence can be best assigned by con- structing an interpretation of the whole sen- tence. This interpretation is facilitated by a dependency-like context specification of a content word within the sentence. Thus, finding the context words of a target word is a matter of finding a pseudo-syntactic de- pendency analysis of the sentence, called a linkage. 1 Introduction Word Sense Disambiguation (WSD) is a difficult Natural Language Processing task which requires that for every content word (noun, adjective, verb or adverb) the appropriate meaning is automatically selected from the available sense inventory1. Tradi- tionally, the WSD algorithms are divided into two rough classes: supervised and unsupervised. The supervised paradigm relies on sense annotated cor- pora, with the assumption that neighbouring disam- biguate words provide a strongly discriminating and generalizable context representation for the meaning of a target word. Obviously, this approach suffers from the knowledge acquisition bottleneck in that 1In principle, one can select meanings for any part of speech that is represented into the semantic lexicon (prepositions for instance) but the content words disambiguation is the de facto standard. there will never be enough training data to ensure a scalable result of such algorithms. The unsuper- vised alternative to WSD tries to alleviate the burden of manually sense tagging the corpora, by employ- ing algorithms that use different knowledge sources to determine the correct meaning in context. In fact, the “knowledge source usage” is another way to dis- tinguish among the WSD methods. Such methods call upon further processing of the text to be dis- ambiguated such as parsing and/or use handcrafted, semantically rich sense inventories such as Word- Net (Fellbaum, 1998). WSD methods in this cate- gory range from the very simple ranking based on counting the number of words occurring in both the target word’s context and its sense definitions in a reference dictionary (Lesk, 1986) to the more elabo- rated approaches using the semantic lexicon’s tax- onomies, (shallow) parsing, collocation discovery etc. (Stevenson and Wilks, 2001). One of the central issues of any WSD implemen- tation is given by the context representation. The standard principle that is applied when trying to dis- ambiguate the meaning of a word is that the same word in similar contexts should have the same mean- ing. By and large, the context of a target word is ma- terialized by a collection of features among which are: the collocates of the target word, the part-of- speech (POS) of the target word, …

Content truncated to 500 words