Mapping the Paraphrase Database to WordNet

Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (*SEM 2017), pages 84–90, Vancouver, Canada, August 3-4, 2017. c⃝2017 Association for Computational Linguistics Mapping the Paraphrase Database to WordNet Anne Cocos∗, Marianna Apidianaki∗♠ and Chris Callison-Burch∗ ∗ Computer and Information Science Department, University of Pennsylvania ♠ LIMSI, CNRS, Universit´e Paris-Saclay, 91403 Orsay {acocos,marapi,ccb}@seas.upenn.edu Abstract WordNet has facilitated important re- search in natural language processing but its usefulness is somewhat limited by its relatively small lexical coverage. The Paraphrase Database (PPDB) covers 650 times more words, but lacks the semantic structure of WordNet that would make it more directly useful for downstream tasks. We present a method for mapping words from PPDB to WordNet synsets with 89% accuracy. The mapping also lays impor- tant groundwork for incorporating Word- Net’s relations into PPDB so as to increase its utility for semantic reasoning in appli- cations. 1 Introduction WordNet (Miller, 1995; Fellbaum, 1998) is one of the most important resources for natural language processing research. Despite its utility, Word- Net1 is manually compiled and therefore relatively small. It contains roughly 155k words, which does not approach web scale, and very few informal or colloquial words, domain-specific terms, new word uses, or named entities. Researchers have compiled several larger, automatically-generated thesaurus-like resources (Lin and Pantel, 2001; Dolan and Brockett, 2005; Navigli and Ponzetto, 2012; Vila et al., 2015). One of these is the Paraphrase Database (PPDB) (Ganitkevitch et al., 2013; Pavlick et al., 2015b). With over 100 million paraphrase pairs, PPDB dwarfs WordNet in size but it lacks WordNet’s semantic structure. Para- phrases for a given word are indistinguishable by sense, and PPDB’s only inherent semantic rela- tional information is predicted entailment relations between word types (Pavlick et al., 2015a). Sev- eral earlier studies attempted to incorporate se- 1In this work we refer specifically to WordNet version 3.0 RULE-PRESCRIPT: imperative*, demand*, duty*, re- quest, gun, decree, ranking RULE-REGULATION: constraint*, limit*, derogation*, notion RULE-FORMULA: method*, standard*, plan*, proceed- ing RULE-LINGUISTIC RULE: notion Table 1: Example of our model’s top-ranked para- phrases for three WordNet synsets for rule (n). Starred paraphrases have a predicted likelihood of attachment of at least 95%; others have predicted likelihood of at least 50%. Bold text indicates paraphrases that match the correct sense of rule. mantic awareness into PPDB, either by clustering its paraphrases by word sense (Apidianaki et al., 2014; Cocos and Callison-Burch, 2016) or choos- ing appropriate PPDB paraphrases for a given con- text (Apidianaki, 2016; Cocos et al., 2017). In this work, we aim to marry the rich semantic knowledge in WordNet with the massive scale of PPDB by predicting WordNet synset membership for PPDB paraphrases that do not appear in Word- Net. Our goal is to increase the lexical coverage of WordNet and incorporate some of the rich rela- tional information from WordNet into PPDB. Ta- ble 1 shows our model’s top-ranked outputs map- ping PPDB paraphrases for the word rule onto their corresponding WordNet synsets. Our overall objective in this work is to map …

Content truncated to 500 words