CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement Learning
By Zeqiu Wu, Yi Luan, Hannah Rashkin, David Reitter, Gaurav Singh Tomar. 2021
113 citations recorded by the source corpus.
Compared to standard retrieval tasks, passage retrieval for conversational question answering (CQA) poses new challenges in understanding the current user question, as each question needs to be interpreted within the dialogue context. Moreover, it can be expensive to re-train well-established retrievers such as search engines that are originally developed for non-conversational queries. To facilitate their use, we develop a query rewriting model CONQRR that rewrites a conversational question in the context into a standalone question. It is trained with a novel reward function to directly optimize towards retrieval using reinforcement learning and can be adapted to any off-the-shelf retriever. CONQRR achieves state-of-the-art results on a recent open-domain CQA dataset containing conversations from three different sources, and is effective for two different off-the-shelf retrievers. Our extensive analysis also shows the robustness of CONQRR to out-of-domain dialogues as well as to zero query rewriting supervision.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing, Reinforcement Learning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Luke S. Zettlemoyer
- Mohit Bansal
- Hinrich Schütze
- Timo Schick
- Yejin Choi
- Jianfeng Gao
- Thomas Scialom
- Hannaneh Hajishirzi
In Computer Vision and Pattern Recognition
- Mohit Bansal
- Ramakanth Pasunuru
- Asli Celikyilmaz
- Edouard Grave
- Thomas Scialom
- Timo Schick
- Jianfeng Gao
- Luc Van Gool
In Natural Language Processing
- Timo Schick
- Asli Celikyilmaz
- Thomas Scialom
- Hinrich Schütze
- Edouard Grave
- Yejin Choi
- Luke S. Zettlemoyer
- Maria Lomeli
In Reinforcement Learning
- Ramakanth Pasunuru
- Yann LeCun
- Asli Celikyilmaz
- Kelvin Guu
- Arun Tejasvi Chaganty
- Christoforos Nalmpantis
- Roberta Raileanu
- Thomas Scialom
Citations in the corpus
- Augmented Language Models: a Survey (2023, methodology): “…al., 2019), or solve the sub-problems sequentially, where the solution to the next sub-problem depends on the answer to the previous ones (Yang et al., 2022a; Zhou et al., 2022; Drozdov et al., 2022; Dua et al., 2022; Khot et al., 2022; Wang et al., 2022a; Wu et al., 2022b; Mishra and Nouri, 2022).”
- Dialog Inpainting: Turning Documents into Dialogs (2022, methodology): “Following prior work (Qu et al., 2020; Yu et al., 2021; Wu et al., 2021), we use only the current and previous questions as inputs for OR-QuAC, TREC CAsT-19 and CAsT-20, and use previous answers in addition to these as input for QReCC.”