@inproceedings{sun-etal-2023-improving,
title = "Improving Contextual Query Rewrite for Conversational {AI} Agents through User-preference Feedback Learning",
author = "Sun, Zhongkai and
Zhou, Yingxue and
Hao, Jie and
Fan, Xing and
Lu, Yanbin and
Ma, Chengyuan and
Shen, Wei and
Guo, Chenlei",
editor = "Wang, Mingxuan and
Zitouni, Imed",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-industry.41",
doi = "10.18653/v1/2023.emnlp-industry.41",
pages = "432--439",
abstract = "Contextual query rewriting (CQR) is a crucial component in Conversational AI agents, leveraging the contextual information from previous user-agent conversations to improve the comprehension of current user intent. However, traditional CQR methods often concentrate on supervised fine-tuning only, neglecting the opportunities to learn from user feedback to align with user preferences. Inspired by recent advances in learning from human feedback (LHF), this paper proposes a novel Preference Aligned Contextual Query Rewriting (PA-CQR) framework to enhance the CQR model{'}s capability in generating user preference-aligned rewrites. This paper also investigates the efficacy of various state-of-the-art feedback learning algorithms on the CQR task, and proposes a novel Dynamic Direct Preference Optimization (Dynamic DPO) algorithm to better adapt the DPO algorithm to large-scale CQR training. Experiments on large-scale real-world CQR data set demonstrate the superiority of the proposed PA-CQR framework and the Dynamic DPO.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sun-etal-2023-improving">
<titleInfo>
<title>Improving Contextual Query Rewrite for Conversational AI Agents through User-preference Feedback Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhongkai</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yingxue</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Hao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xing</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanbin</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengyuan</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenlei</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mingxuan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imed</namePart>
<namePart type="family">Zitouni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Contextual query rewriting (CQR) is a crucial component in Conversational AI agents, leveraging the contextual information from previous user-agent conversations to improve the comprehension of current user intent. However, traditional CQR methods often concentrate on supervised fine-tuning only, neglecting the opportunities to learn from user feedback to align with user preferences. Inspired by recent advances in learning from human feedback (LHF), this paper proposes a novel Preference Aligned Contextual Query Rewriting (PA-CQR) framework to enhance the CQR model’s capability in generating user preference-aligned rewrites. This paper also investigates the efficacy of various state-of-the-art feedback learning algorithms on the CQR task, and proposes a novel Dynamic Direct Preference Optimization (Dynamic DPO) algorithm to better adapt the DPO algorithm to large-scale CQR training. Experiments on large-scale real-world CQR data set demonstrate the superiority of the proposed PA-CQR framework and the Dynamic DPO.</abstract>
<identifier type="citekey">sun-etal-2023-improving</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-industry.41</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-industry.41</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>432</start>
<end>439</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Contextual Query Rewrite for Conversational AI Agents through User-preference Feedback Learning
%A Sun, Zhongkai
%A Zhou, Yingxue
%A Hao, Jie
%A Fan, Xing
%A Lu, Yanbin
%A Ma, Chengyuan
%A Shen, Wei
%A Guo, Chenlei
%Y Wang, Mingxuan
%Y Zitouni, Imed
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F sun-etal-2023-improving
%X Contextual query rewriting (CQR) is a crucial component in Conversational AI agents, leveraging the contextual information from previous user-agent conversations to improve the comprehension of current user intent. However, traditional CQR methods often concentrate on supervised fine-tuning only, neglecting the opportunities to learn from user feedback to align with user preferences. Inspired by recent advances in learning from human feedback (LHF), this paper proposes a novel Preference Aligned Contextual Query Rewriting (PA-CQR) framework to enhance the CQR model’s capability in generating user preference-aligned rewrites. This paper also investigates the efficacy of various state-of-the-art feedback learning algorithms on the CQR task, and proposes a novel Dynamic Direct Preference Optimization (Dynamic DPO) algorithm to better adapt the DPO algorithm to large-scale CQR training. Experiments on large-scale real-world CQR data set demonstrate the superiority of the proposed PA-CQR framework and the Dynamic DPO.
%R 10.18653/v1/2023.emnlp-industry.41
%U https://aclanthology.org/2023.emnlp-industry.41
%U https://doi.org/10.18653/v1/2023.emnlp-industry.41
%P 432-439
Markdown (Informal)
[Improving Contextual Query Rewrite for Conversational AI Agents through User-preference Feedback Learning](https://aclanthology.org/2023.emnlp-industry.41) (Sun et al., EMNLP 2023)
ACL