End-to-End Neural Discourse Deixis Resolution in Dialogue

Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 11322 - 11334 December 7-11, 2022 ©2022 Association for Computational Linguistics End-to-End Neural Discourse Deixis Resolution in Dialogue Shengjie Li and Vincent Ng Human Language Technology Research Institute University of Texas at Dallas Richardson, TX 75083-0688 {sxl180006,vince}@hlt.utdallas.edu Abstract We adapt Lee et al.’s (2018) span-based entity coreference model to the task of end-to-end discourse deixis resolution in dialogue, specif- ically by proposing extensions to their model that exploit task-specific characteristics. The resulting model, dd-utt, achieves state-of- the-art results on the four datasets in the CODI- CRAC 2021 shared task. 1 Introduction Discourse deixis (DD) resolution, also known as ab- stract anaphora resolution, is an under-investigated task that involves resolving a deictic anaphor to its antecedent. A deixis is a reference to a discourse entity such as a proposition, a description, an event, or a speech act (Webber, 1991). DD resolution is arguably more challenging than the extensively- investigated entity coreference resolution task. Re- call that in entity coreference, the goal is to cluster the entity mentions in narrative text or dialogue, which are composed of pronouns, names, and nom- inals, so that the mentions in each cluster refer to the same real-world entity. Lexical overlap is a strong indicator of entity coreference, both among names (e.g., “President Biden”, “Joe Biden”) and in the resolution of nominals (e.g., linking “the presi- dent” to “President Biden”). DD resolution, on the other hand, can be viewed as a generalized case of event coreference involving the clustering of deictic anaphors, which can be pronouns or nominals, and clauses, such that the mentions in each cluster re- fer to the same real-world proposition/event/speech act, etc. The first example in Figure 1 is an exam- ple of DD resolution in which the deictic anaphor “the move” refers to Salomon’s act of issuing war- rants on shares described in the preceding sentence. DD resolution is potentially more challenging than entity coreference resolution because (1) DD res- olution involves understanding clause semantics since antecedents are clauses, and clause semantics Salomon Brothers International Ltd. announced it will is- sue warrants on shares of Hong Kong Telecommunications Ltd. The move closely follows a similar offer by Salomon of warrants for shares of Hongkong & Shanghai Banking Corp. A: Would you donate to Save the Children? B: Yes, I will do $10 to both. B: I am of a tight budget, but I do make room for good causes. A: Thank you very much. A: The children will appreciate it. Figure 1: Examples of discourse deixis resolution. In each example, the deictic anaphor is italicized and the antecedent is boldfaced. are arguably harder to encode than noun phrase semantics; and (2) string matching plays little role in DD resolution, unlike in entity coreference. In this paper, we focus on end-to-end DD res- olution in dialogue. The second example in Fig- ure 1 shows a dialogue between A and B in which the deictic anaphor “it” refers to the …

Content truncated to 500 words