@inproceedings{wang-etal-2021-cleve,
title = "{CLEVE}: {C}ontrastive {P}re-training for {E}vent {E}xtraction",
author = "Wang, Ziqi and
Wang, Xiaozhi and
Han, Xu and
Lin, Yankai and
Hou, Lei and
Liu, Zhiyuan and
Li, Peng and
Li, Juanzi and
Zhou, Jie",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.491",
doi = "10.18653/v1/2021.acl-long.491",
pages = "6283--6297",
abstract = "Event extraction (EE) has considerably benefited from pre-trained language models (PLMs) by fine-tuning. However, existing pre-training methods have not involved modeling event characteristics, resulting in the developed EE models cannot take full advantage of large-scale unsupervised data. To this end, we propose CLEVE, a contrastive pre-training framework for EE to better learn event knowledge from large unsupervised data and their semantic structures (e.g. AMR) obtained with automatic parsers. CLEVE contains a text encoder to learn event semantics and a graph encoder to learn event structures respectively. Specifically, the text encoder learns event semantic representations by self-supervised contrastive learning to represent the words of the same events closer than those unrelated words; the graph encoder learns event structure representations by graph contrastive pre-training on parsed event-related semantic structures. The two complementary representations then work together to improve both the conventional supervised EE and the unsupervised {``}liberal{''} EE, which requires jointly extracting events and discovering event schemata without any annotated data. Experiments on ACE 2005 and MAVEN datasets show that CLEVE achieves significant improvements, especially in the challenging unsupervised setting. The source code and pre-trained checkpoints can be obtained from \url{https://github.com/THU-KEG/CLEVE}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2021-cleve">
<titleInfo>
<title>CLEVE: Contrastive Pre-training for Event Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ziqi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaozhi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xu</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yankai</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Hou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peng</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juanzi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Event extraction (EE) has considerably benefited from pre-trained language models (PLMs) by fine-tuning. However, existing pre-training methods have not involved modeling event characteristics, resulting in the developed EE models cannot take full advantage of large-scale unsupervised data. To this end, we propose CLEVE, a contrastive pre-training framework for EE to better learn event knowledge from large unsupervised data and their semantic structures (e.g. AMR) obtained with automatic parsers. CLEVE contains a text encoder to learn event semantics and a graph encoder to learn event structures respectively. Specifically, the text encoder learns event semantic representations by self-supervised contrastive learning to represent the words of the same events closer than those unrelated words; the graph encoder learns event structure representations by graph contrastive pre-training on parsed event-related semantic structures. The two complementary representations then work together to improve both the conventional supervised EE and the unsupervised “liberal” EE, which requires jointly extracting events and discovering event schemata without any annotated data. Experiments on ACE 2005 and MAVEN datasets show that CLEVE achieves significant improvements, especially in the challenging unsupervised setting. The source code and pre-trained checkpoints can be obtained from https://github.com/THU-KEG/CLEVE.</abstract>
<identifier type="citekey">wang-etal-2021-cleve</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.491</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.491</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>6283</start>
<end>6297</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CLEVE: Contrastive Pre-training for Event Extraction
%A Wang, Ziqi
%A Wang, Xiaozhi
%A Han, Xu
%A Lin, Yankai
%A Hou, Lei
%A Liu, Zhiyuan
%A Li, Peng
%A Li, Juanzi
%A Zhou, Jie
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F wang-etal-2021-cleve
%X Event extraction (EE) has considerably benefited from pre-trained language models (PLMs) by fine-tuning. However, existing pre-training methods have not involved modeling event characteristics, resulting in the developed EE models cannot take full advantage of large-scale unsupervised data. To this end, we propose CLEVE, a contrastive pre-training framework for EE to better learn event knowledge from large unsupervised data and their semantic structures (e.g. AMR) obtained with automatic parsers. CLEVE contains a text encoder to learn event semantics and a graph encoder to learn event structures respectively. Specifically, the text encoder learns event semantic representations by self-supervised contrastive learning to represent the words of the same events closer than those unrelated words; the graph encoder learns event structure representations by graph contrastive pre-training on parsed event-related semantic structures. The two complementary representations then work together to improve both the conventional supervised EE and the unsupervised “liberal” EE, which requires jointly extracting events and discovering event schemata without any annotated data. Experiments on ACE 2005 and MAVEN datasets show that CLEVE achieves significant improvements, especially in the challenging unsupervised setting. The source code and pre-trained checkpoints can be obtained from https://github.com/THU-KEG/CLEVE.
%R 10.18653/v1/2021.acl-long.491
%U https://aclanthology.org/2021.acl-long.491
%U https://doi.org/10.18653/v1/2021.acl-long.491
%P 6283-6297
Markdown (Informal)
[CLEVE: Contrastive Pre-training for Event Extraction](https://aclanthology.org/2021.acl-long.491) (Wang et al., ACL-IJCNLP 2021)
ACL
- Ziqi Wang, Xiaozhi Wang, Xu Han, Yankai Lin, Lei Hou, Zhiyuan Liu, Peng Li, Juanzi Li, and Jie Zhou. 2021. CLEVE: Contrastive Pre-training for Event Extraction. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 6283–6297, Online. Association for Computational Linguistics.