EMNLP 2023short findings0 citations
Multi-Granularity Information Interaction Framework for Incomplete Utterance Rewriting
Haowei Du, Dinghao Zhang, Chen Li, Yang Li, Dongyan Zhao
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.
Incomplete Utterance RewritingInformation InteractionMulti-Granularity
BibTeX
@inproceedings{
du2023multigranularity,
title={Multi-Granularity Information Interaction Framework for Incomplete Utterance Rewriting},
author={Haowei Du and Dinghao Zhang and Chen Li and Yang Li and Dongyan Zhao},
booktitle={The 2023 Conference on Empirical Methods in Natural Language Processing},
year={2023},
url={https://openreview.net/forum?id=rzdqmUFVnv}
}