CREAD: Combined Resolution of Ellipses and Anaphora in Dialogues

TL;DR

This paper introduces a joint learning framework that simultaneously resolves coreferences and rewrites queries in dialogues, significantly improving dialogue understanding and response coherence.

Contribution

It presents a novel joint model for coreference resolution and query rewriting in dialogues, enhancing both tasks and outperforming existing models.

Findings

Query rewrite F1 score improved by 2.3% with coreference modeling.

Joint model outperforms state-of-the-art coreference resolution by 2% F1.

Annotated MuDoCo dataset for coreference resolution with rewritten queries.

Abstract

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.