@inproceedings{yu-etal-2023-improving,
title = "Improving Zero-shot Cross-lingual Dialogue State Tracking via Contrastive Learning",
author = "Yu, Xiang and
Ting, Zhang and
Hui, Di and
Hui, Huang and
Chunyou, Li and
Kazushige, Ouchi and
Yufeng, Chen and
Jinan, Xu",
editor = "Sun, Maosong and
Qin, Bing and
Qiu, Xipeng and
Jiang, Jing and
Han, Xianpei",
booktitle = "Proceedings of the 22nd Chinese National Conference on Computational Linguistics",
month = aug,
year = "2023",
address = "Harbin, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2023.ccl-1.54",
pages = "624--625",
abstract = "{``}Recent works in dialogue state tracking (DST) focus on a handful of languages, as collectinglarge-scale manually annotated data in different languages is expensive. Existing models addressthis issue by code-switched data augmentation or intermediate fine-tuning of multilingual pre-trained models. However, these models can only perform implicit alignment across languages. In this paper, we propose a novel model named Contrastive Learning for Cross-Lingual DST(CLCL-DST) to enhance zero-shot cross-lingual adaptation. Specifically, we use a self-builtbilingual dictionary for lexical substitution to construct multilingual views of the same utterance. Then our approach leverages fine-grained contrastive learning to encourage representations ofspecific slot tokens in different views to be more similar than negative example pairs. By thismeans, CLCL-DST aligns similar words across languages into a more refined language-invariantspace. In addition, CLCL-DST uses a significance-based keyword extraction approach to selecttask-related words to build the bilingual dictionary for better cross-lingual positive examples. Experiment results on Multilingual WoZ 2.0 and parallel MultiWoZ 2.1 datasets show that ourproposed CLCL-DST outperforms existing state-of-the-art methods by a large margin, demon-strating the effectiveness of CLCL-DST.{''}",
language = "English",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yu-etal-2023-improving">
<titleInfo>
<title>Improving Zero-shot Cross-lingual Dialogue State Tracking via Contrastive Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhang</namePart>
<namePart type="family">Ting</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Di</namePart>
<namePart type="family">Hui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huang</namePart>
<namePart type="family">Hui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Chunyou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ouchi</namePart>
<namePart type="family">Kazushige</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Yufeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xu</namePart>
<namePart type="family">Jinan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 22nd Chinese National Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maosong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bing</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xipeng</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xianpei</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Harbin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>“Recent works in dialogue state tracking (DST) focus on a handful of languages, as collectinglarge-scale manually annotated data in different languages is expensive. Existing models addressthis issue by code-switched data augmentation or intermediate fine-tuning of multilingual pre-trained models. However, these models can only perform implicit alignment across languages. In this paper, we propose a novel model named Contrastive Learning for Cross-Lingual DST(CLCL-DST) to enhance zero-shot cross-lingual adaptation. Specifically, we use a self-builtbilingual dictionary for lexical substitution to construct multilingual views of the same utterance. Then our approach leverages fine-grained contrastive learning to encourage representations ofspecific slot tokens in different views to be more similar than negative example pairs. By thismeans, CLCL-DST aligns similar words across languages into a more refined language-invariantspace. In addition, CLCL-DST uses a significance-based keyword extraction approach to selecttask-related words to build the bilingual dictionary for better cross-lingual positive examples. Experiment results on Multilingual WoZ 2.0 and parallel MultiWoZ 2.1 datasets show that ourproposed CLCL-DST outperforms existing state-of-the-art methods by a large margin, demon-strating the effectiveness of CLCL-DST.”</abstract>
<identifier type="citekey">yu-etal-2023-improving</identifier>
<location>
<url>https://aclanthology.org/2023.ccl-1.54</url>
</location>
<part>
<date>2023-08</date>
<extent unit="page">
<start>624</start>
<end>625</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Zero-shot Cross-lingual Dialogue State Tracking via Contrastive Learning
%A Yu, Xiang
%A Ting, Zhang
%A Hui, Di
%A Hui, Huang
%A Chunyou, Li
%A Kazushige, Ouchi
%A Yufeng, Chen
%A Jinan, Xu
%Y Sun, Maosong
%Y Qin, Bing
%Y Qiu, Xipeng
%Y Jiang, Jing
%Y Han, Xianpei
%S Proceedings of the 22nd Chinese National Conference on Computational Linguistics
%D 2023
%8 August
%I Chinese Information Processing Society of China
%C Harbin, China
%G English
%F yu-etal-2023-improving
%X “Recent works in dialogue state tracking (DST) focus on a handful of languages, as collectinglarge-scale manually annotated data in different languages is expensive. Existing models addressthis issue by code-switched data augmentation or intermediate fine-tuning of multilingual pre-trained models. However, these models can only perform implicit alignment across languages. In this paper, we propose a novel model named Contrastive Learning for Cross-Lingual DST(CLCL-DST) to enhance zero-shot cross-lingual adaptation. Specifically, we use a self-builtbilingual dictionary for lexical substitution to construct multilingual views of the same utterance. Then our approach leverages fine-grained contrastive learning to encourage representations ofspecific slot tokens in different views to be more similar than negative example pairs. By thismeans, CLCL-DST aligns similar words across languages into a more refined language-invariantspace. In addition, CLCL-DST uses a significance-based keyword extraction approach to selecttask-related words to build the bilingual dictionary for better cross-lingual positive examples. Experiment results on Multilingual WoZ 2.0 and parallel MultiWoZ 2.1 datasets show that ourproposed CLCL-DST outperforms existing state-of-the-art methods by a large margin, demon-strating the effectiveness of CLCL-DST.”
%U https://aclanthology.org/2023.ccl-1.54
%P 624-625
Markdown (Informal)
[Improving Zero-shot Cross-lingual Dialogue State Tracking via Contrastive Learning](https://aclanthology.org/2023.ccl-1.54) (Yu et al., CCL 2023)
ACL
- Xiang Yu, Zhang Ting, Di Hui, Huang Hui, Li Chunyou, Ouchi Kazushige, Chen Yufeng, and Xu Jinan. 2023. Improving Zero-shot Cross-lingual Dialogue State Tracking via Contrastive Learning. In Proceedings of the 22nd Chinese National Conference on Computational Linguistics, pages 624–625, Harbin, China. Chinese Information Processing Society of China.