CREAD: Combined Resolution of Ellipses and Anaphora in Dialogues

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3390–3406 June 6–11, 2021. ©2021 Association for Computational Linguistics 3390 CREAD: Combined Resolution of Ellipses and Anaphora in Dialogues Bo-Hsiang Tseng1⇤, Shruti Bhargava2, Jiarui Lu2 Joel Ruben Antony Moniz2, Dhivya Piraviperumal2, Lin Li2, Hong Yu2 1Engineering Department, University of Cambridge, UK 2Apple bht26@cam.ac.uk {shruti_bhargava, jiarui_lu, joelrubenantony_moniz, dhivyaprp, lli9, hong_yu}@apple.com Abstract Anaphora and ellipses are two common phe- nomena in dialogues. Without resolving re- ferring expressions and information omission, dialogue systems may fail to generate con- sistent and coherent responses. Traditionally, anaphora is resolved by coreference resolution and ellipses by query rewrite. In this work, we propose a novel joint learning framework of modeling coreference resolution and query rewriting for complex, multi-turn dialogue un- derstanding. Given an ongoing dialogue be- tween a user and a dialogue assistant, for the user query, our joint learning model first pre- dicts coreference links between the query and the dialogue context, and then generates a self- contained rewritten user query. To evaluate our model, we annotate a dialogue based corefer- ence resolution dataset, MuDoCo, with rewrit- ten queries. Results show that the performance of query rewrite can be substantially boosted (+2.3% F1) with the aid of coreference mod- eling. Furthermore, our joint model outper- forms the state-of-the-art coreference resolu- tion model (+2% F1) on this dataset. 1 Introduction In recent years, dialogue systems have attracted growing interest, and been applied to various sce- narios, ranging from chatbots to task-oriented di- alogues to question answering. Despite rapid progress in dialogue systems, several difficulties remain in the understanding of complex, multi-turn dialogues. Two major problems are anaphora reso- lution (Clark and Manning, 2016a,b) and ellipsis (Kumar and Joshi, 2016) in follow-up turns. Take the dialogue in Figure 1 as an example: ellipsis hap- pens in user turn 2 where the user is asking for the capital of “Costa Rica” without explicitly mentioning the country again; coreference happens in user turn 3 where “the capital” refers to ⇤⇤Work done while the first author was an intern at Apple. Figure 1: An example of a question-answering dia- logue where coreference and ellipsis happen in user query, and the corresponding query rewrite annotation. References to the same entity are highlighted in the same color, and can be resolved by coreference reso- lution modeling. The two system responses in Turn 3 indicate two possible interpretations of the city San Jose by the system. “San Jose”. Without resolving the anaphoric refer- ence and the ellipsis, dialogue systems may fail to generate coherent responses. Query rewrite (Quan et al., 2019) is an approach that converts a context-dependent user query into a self-contained utterance so that it can be understood and executed independent of previous dialogue con- text. This technique can solve many cases where coreference or ellipsis happens. For instance, “the capital” in user turn 3 is changed to “San Jose” in the rewrite. Furthermore, the ellipsis of the country name “Costa Rica” …

Content truncated to 500 words