ACL Findings2023
Search-Oriented Conversational Query Editing
Kelong Mao, Zhicheng Dou, Bang Liu, Hongjin Qian, Fengran Mo, Xiangli Wu, Xiaohua Cheng, Zhao Cao
Abstract
Conversational query rewriting (CQR) realizes conversational search by reformulating the search dialogue into a standalone rewrite. However, existing CQR models either are not learned toward improving the downstream search performance or inefficiently generate the rewrite token-by-token from scratch while neglecting the fact that the search dialogue often has a large overlap with the rewrite. In this paper, we propose EDIRCS, a new text editingbased CQR model tailored for conversational search. In EDIRCS, most of the rewrite tokens are selected from the dialogue in a nonautoregressive fashion and only a few new tokens are generated to supplement the final rewrite, which makes EDIRCS highly efficient. In particular, the learning of EDIRCS is augmented with two search-oriented objectives, including contrastive ranking augmentation and contextualization knowledge transfer, which effectively improve it to select and generate more useful tokens from the view of retrieval. We show that EDIRCS outperforms state-of-theart CQR models on three conversational search benchmarks while having low rewriting latency, and is more robust to out-of-domain search dialogues and long dialogue context.
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.
9 top-tier papers have 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
- Bridging the Gap: From Ad-hoc to Proactive Search in Conversations cites Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
- Bridging the Gap: From Ad-hoc to Proactive Search in Conversations cites Few-Shot Conversational Dense Retrieval
- Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval cites Dense Passage Retrieval for Open-Domain Question Answering
- Interpreting Conversational Dense Retrieval by Rewriting-Enhanced Inversion of Session Embedding cites Dense Passage Retrieval for Open-Domain Question Answering
- Interpreting Conversational Dense Retrieval by Rewriting-Enhanced Inversion of Session Embedding cites Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
- Interpreting Conversational Dense Retrieval by Rewriting-Enhanced Inversion of Session Embedding cites Few-Shot Conversational Dense Retrieval
- Interpreting Conversational Dense Retrieval by Rewriting-Enhanced Inversion of Session Embedding cites Generalizing Conversational Dense Retrieval via LLM-Cognition Data Augmentation
- Generalizing Conversational Dense Retrieval via LLM-Cognition Data Augmentation cites Interpreting Conversational Dense Retrieval by Rewriting-Enhanced Inversion of Session Embedding
- Few-Shot Conversational Dense Retrieval cites Dense Passage Retrieval for Open-Domain Question Answering
- Few-Shot Conversational Dense Retrieval cites Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
- Few-Shot Conversational Dense Retrieval cites Query Resolution for Conversational Search with Limited Supervision
- ConvMix: A Mixed-Criteria Data Augmentation Framework for Conversational Dense Retrieval cites Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
- ConvMix: A Mixed-Criteria Data Augmentation Framework for Conversational Dense Retrieval cites Interpreting Conversational Dense Retrieval by Rewriting-Enhanced Inversion of Session Embedding
- ConvMix: A Mixed-Criteria Data Augmentation Framework for Conversational Dense Retrieval cites Query Resolution for Conversational Search with Limited Supervision
- ConvMix: A Mixed-Criteria Data Augmentation Framework for Conversational Dense Retrieval cites Few-Shot Conversational Dense Retrieval
- ConvMix: A Mixed-Criteria Data Augmentation Framework for Conversational Dense Retrieval cites Generalizing Conversational Dense Retrieval via LLM-Cognition Data Augmentation
- Generalizing Conversational Dense Retrieval via LLM-Cognition Data Augmentation cites Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
- Generalizing Conversational Dense Retrieval via LLM-Cognition Data Augmentation cites Few-Shot Conversational Dense Retrieval
Cited by top-tier papers9
- MaFeRw: Query Rewriting with Multi-Aspect Feedbacks for Retrieval-Augmented Large Language ModelsYujing Wang, Hainan Zhang, Liang Pang, Binghui Guo et al.AAAI 2025 · 15 citations
- Generalizing Conversational Dense Retrieval via LLM-Cognition Data AugmentationHaonan Chen, Zhicheng Dou, Kelong Mao, Jiongnan Liu et al.ACL 2024 · 10 citations
- Bridging the Gap: From Ad-hoc to Proactive Search in ConversationsChuan Meng, Francesco Tonolini, Fengran Mo, Nikolaos Aletras et al.SIGIR 2025 · 9 citations
- Interpreting Conversational Dense Retrieval by Rewriting-Enhanced Inversion of Session EmbeddingYiruo Cheng, Kelong Mao, Zhicheng DouACL 2024 · 7 citations
- ConvMix: A Mixed-Criteria Data Augmentation Framework for Conversational Dense RetrievalFengran Mo, Jinghan Zhang, Yuchen Hui, Jia Ao Sun et al.AAAI 2026 · 7 citations
Builds on11
- Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text RetrievalLee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang et al.ICLR 2021 · 1,547 citations
- Dense Passage Retrieval for Open-Domain Question AnsweringVladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick Lewis et al.EMNLP 2020 · 142 citations
- Query Resolution for Conversational Search with Limited SupervisionNikos Voskarides, Dan Li, Pengjie Ren, Evangelos Kanoulas et al.SIGIR 2020 · 112 citations
- Few-Shot Conversational Dense RetrievalShi Yu, Zhenghao Liu, Chenyan Xiong, Tao Feng et al.SIGIR 2021 · 75 citations
- LEWIS: Levenshtein Editing for Unsupervised Text Style TransferMachel Reid, Victor ZhongACL Findings 2021 · 47 citations
Related papers
- CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement LearningZeqiu Wu, Yi Luan, Hannah Rashkin, David Reitter et al.EMNLP 2022 · 37 citations
- Explicit Query Rewriting for Conversational Dense RetrievalHongjin Qian, Zhicheng DouEMNLP 2022 · 14 citations
- DVCQR: Dual-View Conversational Query Rewriting with Stage-wise Reinforcement LearningChenyi Li, Xinhui Tu, Zaixiang WangACL 2026
- Multi-Faceted Self-Consistent Preference Alignment for Query Rewriting in Conversational SearchZhiyu Cao, Peifeng Li, Qiaoming ZhuACL Findings 2026 · 1 citation
- ConvSearch-R1: Enhancing Query Reformulation for Conversational Search with Reasoning via Reinforcement LearningChangtai Zhu, Siyin Wang, Ruijun Feng, Kai Song et al.EMNLP 2025 · 2 citations
