@inproceedings{he-etal-2022-space,
title = "{SPACE}-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understanding",
author = "He, Wanwei and
Dai, Yinpei and
Hui, Binyuan and
Yang, Min and
Cao, Zheng and
Dong, Jianbo and
Huang, Fei and
Si, Luo and
Li, Yongbin",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.46",
pages = "553--569",
abstract = "Pre-training methods with contrastive learning objectives have shown remarkable success in dialog understanding tasks. However, current contrastive learning solely considers the self-augmented dialog samples as positive samples and treats all other dialog samples as negative ones, which enforces dissimilar representations even for dialogs that are semantically related. In this paper, we propose SPACE-2, a tree-structured pre-trained conversation model, which learns dialog representations from limited labeled dialogs and large-scale unlabeled dialog corpora via semi-supervised contrastive pre-training. Concretely, we first define a general semantic tree structure (STS) to unify the inconsistent annotation schema across different dialog datasets, so that the rich structural information stored in all labeled data can be exploited. Then we propose a novel multi-view score function to increase the relevance of all possible dialogs that share similar STSs and only push away other completely different dialogs during supervised contrastive pre-training. To fully exploit unlabeled dialogs, a basic self-supervised contrastive loss is also added to refine the learned representations. Experiments show that our method can achieve new state-of-the-art results on the DialoGLUE benchmark consisting of seven datasets and four popular dialog understanding tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="he-etal-2022-space">
<titleInfo>
<title>SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanwei</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yinpei</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Binyuan</namePart>
<namePart type="family">Hui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianbo</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luo</namePart>
<namePart type="family">Si</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongbin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</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">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hansaem</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Key-Sun</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pum-Mo</namePart>
<namePart type="family">Ryu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hsin-Hsi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Donatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sadao</namePart>
<namePart type="family">Kurohashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrizia</namePart>
<namePart type="family">Paggio</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>
<name type="personal">
<namePart type="given">Seokhwan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Younggyun</namePart>
<namePart type="family">Hahm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tony</namePart>
<namePart type="given">Kyungil</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrico</namePart>
<namePart type="family">Santus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Bond</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-Hoon</namePart>
<namePart type="family">Na</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Pre-training methods with contrastive learning objectives have shown remarkable success in dialog understanding tasks. However, current contrastive learning solely considers the self-augmented dialog samples as positive samples and treats all other dialog samples as negative ones, which enforces dissimilar representations even for dialogs that are semantically related. In this paper, we propose SPACE-2, a tree-structured pre-trained conversation model, which learns dialog representations from limited labeled dialogs and large-scale unlabeled dialog corpora via semi-supervised contrastive pre-training. Concretely, we first define a general semantic tree structure (STS) to unify the inconsistent annotation schema across different dialog datasets, so that the rich structural information stored in all labeled data can be exploited. Then we propose a novel multi-view score function to increase the relevance of all possible dialogs that share similar STSs and only push away other completely different dialogs during supervised contrastive pre-training. To fully exploit unlabeled dialogs, a basic self-supervised contrastive loss is also added to refine the learned representations. Experiments show that our method can achieve new state-of-the-art results on the DialoGLUE benchmark consisting of seven datasets and four popular dialog understanding tasks.</abstract>
<identifier type="citekey">he-etal-2022-space</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.46</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>553</start>
<end>569</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understanding
%A He, Wanwei
%A Dai, Yinpei
%A Hui, Binyuan
%A Yang, Min
%A Cao, Zheng
%A Dong, Jianbo
%A Huang, Fei
%A Si, Luo
%A Li, Yongbin
%Y Calzolari, Nicoletta
%Y Huang, Chu-Ren
%Y Kim, Hansaem
%Y Pustejovsky, James
%Y Wanner, Leo
%Y Choi, Key-Sun
%Y Ryu, Pum-Mo
%Y Chen, Hsin-Hsi
%Y Donatelli, Lucia
%Y Ji, Heng
%Y Kurohashi, Sadao
%Y Paggio, Patrizia
%Y Xue, Nianwen
%Y Kim, Seokhwan
%Y Hahm, Younggyun
%Y He, Zhong
%Y Lee, Tony Kyungil
%Y Santus, Enrico
%Y Bond, Francis
%Y Na, Seung-Hoon
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F he-etal-2022-space
%X Pre-training methods with contrastive learning objectives have shown remarkable success in dialog understanding tasks. However, current contrastive learning solely considers the self-augmented dialog samples as positive samples and treats all other dialog samples as negative ones, which enforces dissimilar representations even for dialogs that are semantically related. In this paper, we propose SPACE-2, a tree-structured pre-trained conversation model, which learns dialog representations from limited labeled dialogs and large-scale unlabeled dialog corpora via semi-supervised contrastive pre-training. Concretely, we first define a general semantic tree structure (STS) to unify the inconsistent annotation schema across different dialog datasets, so that the rich structural information stored in all labeled data can be exploited. Then we propose a novel multi-view score function to increase the relevance of all possible dialogs that share similar STSs and only push away other completely different dialogs during supervised contrastive pre-training. To fully exploit unlabeled dialogs, a basic self-supervised contrastive loss is also added to refine the learned representations. Experiments show that our method can achieve new state-of-the-art results on the DialoGLUE benchmark consisting of seven datasets and four popular dialog understanding tasks.
%U https://aclanthology.org/2022.coling-1.46
%P 553-569
Markdown (Informal)
[SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understanding](https://aclanthology.org/2022.coling-1.46) (He et al., COLING 2022)
ACL
- Wanwei He, Yinpei Dai, Binyuan Hui, Min Yang, Zheng Cao, Jianbo Dong, Fei Huang, Luo Si, and Yongbin Li. 2022. SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understanding. In Proceedings of the 29th International Conference on Computational Linguistics, pages 553–569, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.