tailieunhanh - Báo cáo khoa học: "Entailment above the word level in distributional semantics"

We introduce two ways to detect entailment using distributional semantic representations of phrases. Our first experiment shows that the entailment relation between adjective-noun constructions and their head nouns (big cat |= cat), once represented as semantic vector pairs, generalizes to lexical entailment among nouns (dog |= animal). Our second experiment shows that a classifier fed semantic vector pairs can similarly generalize the entailment relation among quantifier phrases (many dogs|=some dogs) to entailment involving unseen quantifiers (all cats|=several cats). . | Entailment above the word level in distributional semantics Marco Baroni Ngoc-Quynh Do Chung-chieh Shan Raffaella Bernardi Free University of Bozen-Bolzano Cornell University University of Trento University of Tsukuba ccshan@ Abstract We introduce two ways to detect entailment using distributional semantic representations of phrases. Our first experiment shows that the entailment relation between adjective-noun constructions and their head nouns big cat 1 cat once represented as semantic vector pairs generalizes to lexical entailment among nouns dog animal . Our second experiment shows that a classifier fed semantic vector pairs can similarly generalize the entailment relation among quantifier phrases many dogs some dogs to entailment involving unseen quantifiers all cats several cats . Moreover nominal and quantifier phrase entailment appears to be cued by different distributional correlates as predicted by the type-based view of entailment in formal semantics. 1 Introduction Distributional semantics DS approximates linguistic meaning with vectors summarizing the contexts where expressions occur. The success of DS in lexical semantics has validated the hypothesis that semantically similar expressions occur in similar contexts Landauer and Dumais 1997 Lund and Burgess 1996 Sahlgren 2006 Schutze 1997 Turney and Pantel 2010 . Formal semantics FS represents linguistic meanings as symbolic formulas and assemble them via composition rules. FS has successfully modeled quantification and captured inferential relations between phrases and between sentences Montague 1970 Thomason 1974 Heim and Kratzer 1998 . The strengths of DS and FS have been complementary to date On one hand DS has induced large-scale semantic representations from corpora but it has been largely limited to the lexical domain. On the other hand FS has provided sophisticated models of sentence meaning but it has been largely limited to hand-coded