Multi-Granularity Information Interaction Framework for Incomplete Utterance Rewriting
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913188203724800 |
|---|---|
| author | Du, Haowei Zhang, Dinghao Li, Chen Li, Yang Zhao, Dongyan |
| author_facet | Du, Haowei Zhang, Dinghao Li, Chen Li, Yang Zhao, Dongyan |
| contents | 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 \url{https://github.com/yanmenxue/QR}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_11945 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Multi-Granularity Information Interaction Framework for Incomplete Utterance Rewriting Du, Haowei Zhang, Dinghao Li, Chen Li, Yang Zhao, Dongyan Computation and Language 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 \url{https://github.com/yanmenxue/QR}. |
| title | Multi-Granularity Information Interaction Framework for Incomplete Utterance Rewriting |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2312.11945 |