Improving Hypernymy Detection with an Integrated Path-based and Distributional Method

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, pages 2389–2398, Berlin, Germany, August 7-12, 2016. c⃝2016 Association for Computational Linguistics Improving Hypernymy Detection with an Integrated Path-based and Distributional Method Vered Shwartz Yoav Goldberg Ido Dagan Computer Science Department Bar-Ilan University Ramat-Gan, Israel vered1986@gmail.com yoav.goldberg@gmail.com dagan@cs.biu.ac.il Abstract Detecting hypernymy relations is a key task in NLP, which is addressed in the literature using two complemen- tary approaches. Distributional methods, whose supervised variants are the cur- rent best performers, and path-based meth- ods, which received less research atten- tion. We suggest an improved path-based algorithm, in which the dependency paths are encoded using a recurrent neural net- work, that achieves results comparable to distributional methods. We then ex- tend the approach to integrate both path- based and distributional signals, signifi- cantly improving upon the state-of-the-art on this task. 1 Introduction Hypernymy is an important lexical-semantic rela- tion for NLP tasks. For instance, knowing that Tom Cruise is an actor can help a question an- swering system answer the question “which ac- tors are involved in Scientology?”. While seman- tic taxonomies, like WordNet (Fellbaum, 1998), define hypernymy relations between word types, they are limited in scope and domain. Therefore, automated methods have been developed to deter- mine, for a given term-pair (x, y), whether y is an hypernym of x, based on their occurrences in a large corpus. For a couple of decades, this task has been ad- dressed by two types of approaches: distributional, and path-based. In distributional methods, the de- cision whether y is a hypernym of x is based on the distributional representations of these terms. Lately, with the popularity of word embeddings (Mikolov et al., 2013), most focus has shifted to- wards supervised distributional methods, in which each (x, y) term-pair is represented using some combination of the terms’ embedding vectors. In contrast to distributional methods, in which the decision is based on the separate contexts of x and y, path-based methods base the decision on the lexico-syntactic paths connecting the joint oc- currences of x and y in a corpus. Hearst (1992) identified a small set of frequent paths that indicate hypernymy, e.g. Y such as X. Snow et al. (2004) represented each (x, y) term-pair as the multiset of dependency paths connecting their co-occurrences in a corpus, and trained a classifier to predict hy- pernymy, based on these features. Using individual paths as features results in a huge, sparse feature space. While some paths are rare, they often consist of certain unimportant components. For instance, “Spelt is a species of wheat” and “Fantasy is a genre of fiction” yield two different paths: X be species of Y and X be genre of Y, while both indicating that X is-a Y. A possible solution is to generalize paths by replac- ing words along the path with their part-of-speech tags or with wild cards, as done in the PATTY sys- tem (Nakashole et al., 2012). Overall, the state-of-the-art path-based methods perform worse than the …

Content truncated to 500 words