CREAD: Combined Resolution of Ellipses and Anaphora in Dialogues
This work addresses the challenge of generating consistent and coherent responses in dialogue systems, which is crucial for improving user interactions, though it is incremental as it builds on existing methods.
The paper tackles the problem of resolving anaphora and ellipses in dialogues by proposing a joint learning framework for coreference resolution and query rewriting, resulting in a 2.3% F1 boost in query rewrite and a 2% F1 improvement in coreference resolution over state-of-the-art models.
Anaphora and ellipses are two common phenomena in dialogues. Without resolving referring expressions and information omission, dialogue systems may fail to generate consistent 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 understanding. Given an ongoing dialogue between a user and a dialogue assistant, for the user query, our joint learning model first predicts 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 coreference resolution dataset, MuDoCo, with rewritten queries. Results show that the performance of query rewrite can be substantially boosted (+2.3% F1) with the aid of coreference modeling. Furthermore, our joint model outperforms the state-of-the-art coreference resolution model (+2% F1) on this dataset.