Paraphrasing vs Coreferring: Two Sides of the Same Coin

Findings of the Association for Computational Linguistics: EMNLP 2020, pages 4897–4907 November 16 - 20, 2020. c⃝2020 Association for Computational Linguistics 4897 Paraphrasing vs Coreferring: Two Sides of the Same Coin Yehudit Meged1 Avi Caciularu1,2 Vered Shwartz2,3 Ido Dagan1 1Computer Science Department, Bar-Ilan University, Ramat-Gan, Israel 2Allen Institute for Artificial Intelligence 3Paul G. Allen School of Computer Science & Engineering, University of Washington {yehuditmeged,avi.c33}@gmail.com, vereds@allenai.org, dagan@cs.biu.ac.il Abstract We study the potential synergy between two different NLP tasks, both confronting predi- cate lexical variability: identifying predicate paraphrases, and event coreference resolution. First, we used annotations from an event coreference dataset as distant supervision to re-score heuristically-extracted predicate para- phrases. The new scoring gained more than 18 points in average precision upon their rank- ing by the original scoring method. Then, we used the same re-ranking features as additional inputs to a state-of-the-art event coreference resolution model, which yielded modest but consistent improvements to the model’s perfor- mance. The results suggest a promising direc- tion to leverage data and models for each of the tasks to the benefit of the other. 1 Introduction Recognizing that mentions of different lexical predicates discuss the same event is challenging (Barhom et al., 2019). Lexical resources such as WordNet (Miller, 1995) capture such synonyms (say, tell) and hypernyms (whisper, talk), as well as antonyms, which can be used to refer to the same event when the arguments are reversed ([a]0 beat [a]1, [a]1 lose to [a]0). However, WordNet’s cov- erage is insufficient, in particular, missing context- specific paraphrases (e.g. (hide, launder), in the context of money). Conversely, distributional meth- ods enjoy broader coverage, but their precision for this purpose is limited because distributionally sim- ilar terms may often be mutually-exclusive (born, die) or may refer to different event types which are only temporally or causally related (sentenced, convicted). Two prominent lines of work pertaining to iden- tifying predicates whose meaning or referents can be matched are cross-document (CD) event coref- erence resolution and recognizing predicate para- Tara Reid has checked into∨ Promises Treatment Center. Actress Tara Reid entered∨ well-known Malibu rehab center. Lindsay Lohan checked into× rehab in Malibu, California. Director Chris Weitz is expected to direct∨ New Moon. Chris Weitz will take on∨ the sequel to “Twilight”. Gary Ross is still in negotiations to direct× the sequel. Table 1: Examples from ECB+ (a cross-document coreference dataset) that illustrate the context-sensitive nature of event coreference. The illustrated predicates are co-referable, and hence may be used to refer to the same event in certain contexts, but obviously not all their mentions corefer. phrases. The former identifies and clusters event mentions, across multiple documents, that refer to the same event within their respective contexts. The latter task, on the other hand, collects pairs of event expressions that, at the generic lexical level, may refer to the same event in certain contexts. Table 1 illustrates this difference with examples of co-referable predicate paraphrases, while their mentions obviously do not always co-refer. Cross-document event coreference resolution systems are typically supervised, …

Content truncated to 500 words