Multi-Granularity Information Interaction Framework for Incomplete Utterance Rewriting

Haowei Du, Dinghao Zhang, Chen Li, Yang Li, Dongyan Zhao

Submission Type: Regular Short Paper

Submission Track: NLP Applications

Submission Track 2: Question Answering

Keywords: Incomplete Utterance Rewriting, Information Interaction, Multi-Granularity

Abstract:

Recent approaches in Incomplete Utterance Rewriting (IUR) fail to capture the source of important words, which is crucial to edit the incomplete utterance, and introduce words from irrelevant utterances. We propose a novel and effective multi-task information interaction framework including context selection, edit matrix construction, and relevance merging to capture
the multi-granularity of semantic information. Benefiting from fetching the relevant utterance and figuring out the important words,
our approach outperforms existing state-of-the-art models on two benchmark datasets Restoration-200K and CANAND in this field.

Submission Number: 3907