@inproceedings{yuan-etal-2024-co3-low,
title = "{CO}3: Low-resource Contrastive Co-training for Generative Conversational Query Rewrite",
author = "Yuan, Yifei and
Shi, Chen and
Runze, Wang and
Chen, Liyi and
Hu, Renjun and
Zhang, Zengming and
Jiang, Feijun and
Lam, Wai",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.301",
pages = "3394--3406",
abstract = "Generative query rewrite generates reconstructed query rewrites using the conversation history while rely heavily on gold rewrite pairs that are expensive to obtain. Recently, few-shot learning is gaining increasing popularity for this task, whereas these methods are sensitive to the inherent noise due to limited data size. Besides, both attempts face performance degradation when there exists language style shift between training and testing cases. To this end, we study low-resource generative conversational query rewrite that is robust to both noise and language style shift. The core idea is to utilize massive unlabeled data to make further improvements via a contrastive co-training paradigm. Specifically, we co-train two dual models (namely Rewriter and Simplifier) such that each of them provides extra guidance through pseudo-labeling for enhancing the other in an iterative manner. We also leverage contrastive learning with data augmentation, which enables our model pay more attention on the truly valuable information than the noise. Extensive experiments demonstrate the superiority of our model under both few-shot and zero-shot scenarios. We also verify the better generalization ability of our model when encountering language style shift.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yuan-etal-2024-co3-low">
<titleInfo>
<title>CO3: Low-resource Contrastive Co-training for Generative Conversational Query Rewrite</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yifei</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wang</namePart>
<namePart type="family">Runze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liyi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Renjun</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zengming</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Feijun</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wai</namePart>
<namePart type="family">Lam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Generative query rewrite generates reconstructed query rewrites using the conversation history while rely heavily on gold rewrite pairs that are expensive to obtain. Recently, few-shot learning is gaining increasing popularity for this task, whereas these methods are sensitive to the inherent noise due to limited data size. Besides, both attempts face performance degradation when there exists language style shift between training and testing cases. To this end, we study low-resource generative conversational query rewrite that is robust to both noise and language style shift. The core idea is to utilize massive unlabeled data to make further improvements via a contrastive co-training paradigm. Specifically, we co-train two dual models (namely Rewriter and Simplifier) such that each of them provides extra guidance through pseudo-labeling for enhancing the other in an iterative manner. We also leverage contrastive learning with data augmentation, which enables our model pay more attention on the truly valuable information than the noise. Extensive experiments demonstrate the superiority of our model under both few-shot and zero-shot scenarios. We also verify the better generalization ability of our model when encountering language style shift.</abstract>
<identifier type="citekey">yuan-etal-2024-co3-low</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.301</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>3394</start>
<end>3406</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CO3: Low-resource Contrastive Co-training for Generative Conversational Query Rewrite
%A Yuan, Yifei
%A Shi, Chen
%A Runze, Wang
%A Chen, Liyi
%A Hu, Renjun
%A Zhang, Zengming
%A Jiang, Feijun
%A Lam, Wai
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F yuan-etal-2024-co3-low
%X Generative query rewrite generates reconstructed query rewrites using the conversation history while rely heavily on gold rewrite pairs that are expensive to obtain. Recently, few-shot learning is gaining increasing popularity for this task, whereas these methods are sensitive to the inherent noise due to limited data size. Besides, both attempts face performance degradation when there exists language style shift between training and testing cases. To this end, we study low-resource generative conversational query rewrite that is robust to both noise and language style shift. The core idea is to utilize massive unlabeled data to make further improvements via a contrastive co-training paradigm. Specifically, we co-train two dual models (namely Rewriter and Simplifier) such that each of them provides extra guidance through pseudo-labeling for enhancing the other in an iterative manner. We also leverage contrastive learning with data augmentation, which enables our model pay more attention on the truly valuable information than the noise. Extensive experiments demonstrate the superiority of our model under both few-shot and zero-shot scenarios. We also verify the better generalization ability of our model when encountering language style shift.
%U https://aclanthology.org/2024.lrec-main.301
%P 3394-3406
Markdown (Informal)
[CO3: Low-resource Contrastive Co-training for Generative Conversational Query Rewrite](https://aclanthology.org/2024.lrec-main.301) (Yuan et al., LREC-COLING 2024)
ACL
- Yifei Yuan, Chen Shi, Wang Runze, Liyi Chen, Renjun Hu, Zengming Zhang, Feijun Jiang, and Wai Lam. 2024. CO3: Low-resource Contrastive Co-training for Generative Conversational Query Rewrite. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 3394–3406, Torino, Italia. ELRA and ICCL.