GECOR: An End-to-End Generative Ellipsis and Co-reference Resolution Model for Task-Oriented Dialogue

TL;DR

This paper introduces GECOR, an end-to-end generative model for resolving ellipsis and co-reference in dialogue, improving task completion success in task-oriented dialogue systems.

Contribution

The paper proposes a novel unified generative model for ellipsis and co-reference resolution integrated into dialogue systems, with a new annotated dataset for training.

Findings

GECOR outperforms seq2seq baseline in resolution accuracy.

Multi-task framework with GECOR improves task success rate.

Constructed dataset enhances training for ellipsis and co-reference resolution.

Abstract

Ellipsis and co-reference are common and ubiquitous especially in multi-turn dialogues. In this paper, we treat the resolution of ellipsis and co-reference in dialogue as a problem of generating omitted or referred expressions from the dialogue context. We therefore propose a unified end-to-end Generative Ellipsis and CO-reference Resolution model (GECOR) in the context of dialogue. The model can generate a new pragmatically complete user utterance by alternating the generation and copy mode for each user utterance. A multi-task learning framework is further proposed to integrate the GECOR into an end-to-end task-oriented dialogue. In order to train both the GECOR and the multi-task learning framework, we manually construct a new dataset on the basis of the public dataset CamRest676 with both ellipsis and co-reference annotation. On this dataset, intrinsic evaluations on the resolution of ellipsis and co-reference show that the GECOR model significantly outperforms the sequence-to-sequence (seq2seq) baseline model in terms of EM, BLEU and F1 while extrinsic evaluations on the downstream dialogue task demonstrate that our multi-task learning framework with GECOR achieves a higher success rate of task completion than TSCP, a state-of-the-art end-to-end task-oriented dialogue model.