For instance, in a task such as Textual Entailment it is crucial not only to identify whether two words are semantically similar, but also whether they entail each other, like hyponym-hypernym pairs do. This loose definition, therefore, poses a big challenge in Natural Language Processing (NLP), and in particular in Computational Lexical Semantics, where the meaning of a word and the type of relations it holds with others need to be univocally identified. As a consequence of such definition, words like dog may be considered similar not only to the co-hyponym lexeme cat, but also to the hypernym animal, the meronym tail (Morlane-Hondère, 2015), and so on. co-hyponyms and near-synonyms), but – more in general – all those words that share many contexts (Harris, 1954). This representation is so effective that DSMs are known to be able to replicate human judgments with a reasonable accuracy (Lenci, 2008).ģHowever, the Distributional Hypothesis shapes the concept of similarity in a very loose way, including among the distributionally similar words not only those that refer to similar referents (e.g. This, in turn, can be calculated through the vector cosine (Turney and Pantel, 2010). They represent words as vectors in a continuous vector space, where distributional similarity can be measured as vector proximity. Distributional Semantic Models (DSMs) encoding the frequency of co-occurrences between words in large corpora are proven to be successful in representing word meanings in terms of distributional similarity (Turney and Pantel, 2010 PadoÏ and Lapata, 2007 Sahlgren, 2006).ĢThese models allow a geometric representation of the Distributional Hypothesis (Harris, 1954), that is, words occurring in similar contexts also have similar meanings. IntroductionġSimilarity is one of the fundamental principles organizing the semantic lexicon (Lenci, 2008 Landauer and Dumais, 1997). This work is partially supported by HK PhD Fellowship Scheme under PF12-13656. During the evaluation, we have noticed that APAnt also has a particular preference for hypernyms. This paper describes the algorithm in details and analyzes its current limitations, suggesting that extensions may be developed for discriminating antonyms not only from near-synonyms but also from other semantic relations. Evaluation shows that it outperforms three baselines in an antonym retrieval task: the vector cosine, a baseline implementing the co-occurrence hypothesis, and a random rank. The measure – previously introduced in some pilot studies – is presented here with two variants. their average rank in the mutual dependency sorted list of contexts). Such hypothesis has been implemented in APAnt, a distributional measure that evaluates the extent of the intersection among the most relevant contexts of two words (where relevance is measured as mutual dependency), and its saliency (i.e. The discriminating method is based on the hypothesis that, even though both near-synonyms and opposites are mostly distributionally similar, opposites are different from each other in at least one dimension of meaning, which can be assumed to be salient. This paper analyzes the concept of opposition and describes a fully unsupervised method for its automatic discrimination from near-synonymy in Distributional Semantic Models (DSMs).
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |