ACL Findings2023
Incomplete Utterance Rewriting as Sequential Greedy Tagging
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 speakeraware 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-theart models. Furthermore, benefitting from the model's simplicity, our approach outperforms most previous models on inference speed.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Hierarchical Context Tagging for Utterance Rewriting cites SARG: A Novel Semi Autoregressive Generator for Multi-turn Incomplete Utterance Restoration
- Hierarchical Context Tagging for Utterance Rewriting cites Incomplete Utterance Rewriting as Semantic Segmentation
- Incomplete Utterance Rewriting with Editing Operation Guidance and Utterance Augmentation cites SARG: A Novel Semi Autoregressive Generator for Multi-turn Incomplete Utterance Restoration
- Incomplete Utterance Rewriting with Editing Operation Guidance and Utterance Augmentation cites Hierarchical Context Tagging for Utterance Rewriting
- Incomplete Utterance Rewriting with Editing Operation Guidance and Utterance Augmentation cites Incomplete Utterance Rewriting as Semantic Segmentation
- Incomplete Utterance Rewriting with Editing Operation Guidance and Utterance Augmentation cites RAST: Domain-Robust Dialogue Rewriting as Sequence Tagging
- RAST: Domain-Robust Dialogue Rewriting as Sequence Tagging cites SARG: A Novel Semi Autoregressive Generator for Multi-turn Incomplete Utterance Restoration
- RAST: Domain-Robust Dialogue Rewriting as Sequence Tagging cites Incomplete Utterance Rewriting as Semantic Segmentation
Cited by top-tier papers1
Builds on4
- Incomplete Utterance Rewriting as Semantic SegmentationQian Liu, Bei Chen, Jian-Guang Lou, Bin Zhou et al.EMNLP 2020 · 51 citations
- SARG: A Novel Semi Autoregressive Generator for Multi-turn Incomplete Utterance RestorationMengzuo Huang, Feng Li, Wuhe Zou, Weidong ZhangAAAI 2021 · 27 citations
- Hierarchical Context Tagging for Utterance RewritingLisa Jin, Linfeng Song, Lifeng Jin, Dong Yu et al.AAAI 2022 · 11 citations
- RAST: Domain-Robust Dialogue Rewriting as Sequence TaggingJie Hao, Linfeng Song, Liwei Wang, Kun Xu et al.EMNLP 2021 · 1 citation
Related papers
- Multi-Granularity Information Interaction Framework for Incomplete Utterance RewritingHaowei Du, Dinghao Zhang, Chen Li, Yang Li et al.EMNLP Findings 2023
- Incomplete Utterance Rewriting by A Two-Phase Locate-and-Fill RegimeZitong Li, Jiawei Li, Haifeng Tang, Kenny Q. Zhu et al.ACL Findings 2023 · 1 citation
- Contextualized Rewriting for Text SummarizationGuangsheng Bao, Yue ZhangAAAI 2021 · 17 citations
- Dialogue-Based Relation ExtractionDian Yu, Kai Sun, Claire Cardie, Dong YuACL 2020 · 106 citations
- Dialogue-RAG: Enhancing Retrieval for LLMs via Node-Linking Utterance RewritingQiwei Li, Teng Xiao, Zuchao Li, Ping Wang et al.ACL 2025
