Two-stage Incomplete Utterance Rewriting on Editing Operation
Zhiyu Cao, Peifeng Li, Qiaoming Zhu, Yaxin Fan
Abstract
Previous work on Incomplete Utterance Rewriting (IUR) has primarily focused on generating rewritten utterances based solely on dialogue context, ignoring the widespread phenomenon of coreference and ellipsis in dialogues. To address this issue, we propose a novel framework called TEO (Two-stage approach on Editing Operation) for IUR, in which the first stage generates editing operations and the second stage rewrites incomplete utterances utilizing the generated editing operations and the dialogue context. Furthermore, an adversarial perturbation strategy is proposed to mitigate cascading errors and exposure bias caused by the inconsistency between training and inference in the second stage. Experimental results on three IUR datasets show that our TEO outperforms the SOTA models significantly.
BibTeX
@inproceedings{cao-etal-2025-two,
title = "Two-stage Incomplete Utterance Rewriting on Editing Operation",
author = "Cao, Zhiyu and
Li, Peifeng and
Zhu, Qiaoming and
Fan, Yaxin",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.33/",
pages = "496--507"
}