Improving Multi-turn Dialogue Modelling with Utterance ReWriter

Abstract

Recent research has made impressive progress in single-turn dialogue modelling. In the multi-turn setting, however, current models are still far from satisfactory. One major challenge is the frequently occurred coreference and information omission in our daily conversation, making it hard for machines to understand the real intention. In this paper, we propose rewriting the human utterance as a pre-process to help multi-turn dialgoue modelling. Each utterance is first rewritten to recover all coreferred and omitted information. The next processing steps are then performed based on the rewritten utterance. To properly train the utterance rewriter, we collect a new dataset with human annotations and introduce a Transformer-based utterance rewriting architecture using the pointer network. We show the proposed architecture achieves remarkably good performance on the utterance rewriting task. The trained utterance rewriter can be easily integrated into online chatbots and brings general improvement over different domains.

Accepted to ACL 2019

References in corpus (8)

• A Neural Conversational Model
• Get To The Point: Summarization with Pointer-Generator Networks
• Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting
• Pre-Translation for Neural Machine Translation
• Search Engine Guided Non-Parametric Neural Machine Translation
• An Exploration of Neural Sequence-to-Sequence Architectures for Automatic Post-Editing
• Scaling Multi-Domain Dialogue State Tracking via Query Reformulation
• QuickEdit: Editing Text & Translations by Crossing Words Out

Cited by in corpus (5)

• Learning a Simple and Effective Model for Multi-turn Response Generation with Auxiliary Tasks
• Neural Data-to-Text Generation via Jointly Learning the Segmentation and Correspondence
• Hierarchical Context Tagging for Utterance Rewriting
• Diversifying Dialogue Generation with Non-Conversational Text
• Conversational Semantic Role Labeling