Filling Missing Paths: Modeling Co-occurrences of Word Pairs and Dependency Paths for Recognizing Lexical Semantic Relations

Proceedings of NAACL-HLT 2018, pages 1123–1133 New Orleans, Louisiana, June 1 - 6, 2018. c⃝2018 Association for Computational Linguistics Filling Missing Paths: Modeling Co-occurrences of Word Pairs and Dependency Paths for Recognizing Lexical Semantic Relations Koki Washio and Tsuneaki Kato Department of Language and Information Sciences Graduate School of Arts and Sciences The University of Tokyo 3-8-1, Komaba, Meguroku, Tokyo 153-8902 Japan {kokiwashio@g.ecc, kato@boz.c}.u-tokyo.ac.jp Abstract Recognizing lexical semantic relations be- tween word pairs is an important task for many applications of natural language processing. One of the mainstream approaches to this task is to exploit the lexico-syntactic paths con- necting two target words, which reflect the semantic relations of word pairs. However, this method requires that the considered words co-occur in a sentence. This requirement is hardly satisfied because of Zipf’s law, which states that most content words occur very rarely. In this paper, we propose novel meth- ods with a neural model of P(path|w1, w2) to solve this problem. Our proposed model of P(path|w1, w2) can be learned in an un- supervised manner and can generalize the co- occurrences of word pairs and dependency paths. This model can be used to augment the path data of word pairs that do not co-occur in the corpus, and extract features capturing re- lational information from word pairs. Our ex- perimental results demonstrate that our meth- ods improve on previous neural approaches based on dependency paths and successfully solve the focused problem. 1 Introduction The semantic relations between words are impor- tant for many natural language processing tasks, such as recognizing textual entailment (Dagan et al., 2010) and question answering (Yang et al., 2017). Moreover, these relations have been also used as features for neural methods in machine translation (Sennrich and Haddow, 2016) and re- lation extraction (Xu et al., 2015). This type of information is provided by manually-created se- mantic taxonomies, such as WordNet (Fellbaum, 1998). However, these resources are expensive to expand manually and have limited domain cov- erage. Thus, the automatic detection of lexico- semantic relations has been studied for several decades. One of the most popular approaches is based on patterns that encode a specific kind of relation- ship (synonym, hypernym, etc.) between adjacent words. This type of approach is called a path- based method. Lexico-syntactic patterns between two words provide information on semantic rela- tions. For example, if we see the pattern, “animals such as a dog” in a corpus, we can infer that ani- mal is a hypernym of dog. On the basis of this as- sumption, Hearst (1992) detected the hypernymy relation of two words from a corpus based on sev- eral handcrafted lexico-syntactic patterns, e.g., X such as Y. Snow et al. (2004) used as features in- dicative dependency paths, in which target word pairs co-occurred, and trained a classifier with data to detect hypernymy relations. In recent studies, Shwartz et al. (2016) pro- posed a neural path-based model that encoded dependency paths between two words into low- dimensional dense vectors with recurrent neural …

Content truncated to 500 words