Incomplete Utterance Rewriting as Sequential Greedy Tagging

Yunshan Chen


Abstract
The task of incomplete utterance rewriting has recently gotten much attention. Previous models struggled to extract information from the dialogue context, as evidenced by the low restoration scores. To address this issue, we propose a novel sequence tagging-based model, which is more adept at extracting information from context. Meanwhile, we introduce speaker-aware embedding to model speaker variation. Experiments on multiple public datasets show that our model achieves optimal results on all nine restoration scores while having other metric scores comparable to previous state-of-the-art models. Furthermore, benefitting from the model’s simplicity, our approach outperforms most previous models on inference speed.
Anthology ID:
2023.findings-acl.456
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7265–7276
Language:
URL:
https://aclanthology.org/2023.findings-acl.456
DOI:
10.18653/v1/2023.findings-acl.456
Bibkey:
Cite (ACL):
Yunshan Chen. 2023. Incomplete Utterance Rewriting as Sequential Greedy Tagging. In Findings of the Association for Computational Linguistics: ACL 2023, pages 7265–7276, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Incomplete Utterance Rewriting as Sequential Greedy Tagging (Chen, Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2023.findings-acl.456.pdf