Multi-Granularity Information Interaction Framework for Incomplete Utterance Rewriting
Haowei Du, Dinghao Zhang, Chen Li, Yang Li, Dongyan Zhao
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/yanmenxue/qrOfficialIn paper★ 0
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. Code will be provided on https://github.com/yanmenxue/QR.