CL-ECPE: contrastive learning with adversarial samples for emotion-cause pair extraction

The existing Emotion-Cause Pair Extraction (ECPE) has made some achievements, and it is applied in many tasks, such as criminal investigations. Previous approaches realised extraction by constructing different networks, but they did not fully exploit the original information of the data, which led t...

Full description

Saved in:
Bibliographic Details
Main Authors: Shunxiang Zhang, Houyue Wu, Xin Xu, Guangli Zhu, Meng-Yen Hsieh
Format: Article
Language:English
Published: Taylor & Francis Group 2022-12-01
Series:Connection Science
Subjects:
Online Access:http://dx.doi.org/10.1080/09540091.2022.2082383
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850245382709182464
author Shunxiang Zhang
Houyue Wu
Xin Xu
Guangli Zhu
Meng-Yen Hsieh
author_facet Shunxiang Zhang
Houyue Wu
Xin Xu
Guangli Zhu
Meng-Yen Hsieh
author_sort Shunxiang Zhang
collection DOAJ
description The existing Emotion-Cause Pair Extraction (ECPE) has made some achievements, and it is applied in many tasks, such as criminal investigations. Previous approaches realised extraction by constructing different networks, but they did not fully exploit the original information of the data, which led to low extraction precision. Moreover, the extraction precision will also be decreased when the model is attacked by adversarial samples. To address the above problems, a new model CL-ECPE is proposed in this article to improve the extraction precision through contrastive learning. First, contrastive sets are constructed by adversarial samples. The contrastive sets are used as the raw data of adversarial training and the test data of the pilot experiment. Then, adversarial training is used to get contrastive features according to the training target. The acquisition of contrastive features can improve extraction precision. Experimental results on the benchmark emotion cause corpus show our method outperforms the state-of-the-art method by over 12.49%, as well as demonstrates the strong robustness of CL-ECPE.
format Article
id doaj-art-05e04e9a185d48aa87f8753f97fa728d
institution OA Journals
issn 0954-0091
1360-0494
language English
publishDate 2022-12-01
publisher Taylor & Francis Group
record_format Article
series Connection Science
spelling doaj-art-05e04e9a185d48aa87f8753f97fa728d2025-08-20T01:59:29ZengTaylor & Francis GroupConnection Science0954-00911360-04942022-12-013411877189410.1080/09540091.2022.20823832082383CL-ECPE: contrastive learning with adversarial samples for emotion-cause pair extractionShunxiang Zhang0Houyue Wu1Xin Xu2Guangli Zhu3Meng-Yen Hsieh4School of Computer Science and Engineering, Anhui University of Science and Technology, Huainan, People's Republic of ChinaSchool of Computer Science and Engineering, Anhui University of Science and Technology, Huainan, People's Republic of ChinaSchool of Computer Science and Engineering, Anhui University of Science and Technology, Huainan, People's Republic of ChinaSchool of Computer Science and Engineering, Anhui University of Science and Technology, Huainan, People's Republic of Chinarovidence UniversityThe existing Emotion-Cause Pair Extraction (ECPE) has made some achievements, and it is applied in many tasks, such as criminal investigations. Previous approaches realised extraction by constructing different networks, but they did not fully exploit the original information of the data, which led to low extraction precision. Moreover, the extraction precision will also be decreased when the model is attacked by adversarial samples. To address the above problems, a new model CL-ECPE is proposed in this article to improve the extraction precision through contrastive learning. First, contrastive sets are constructed by adversarial samples. The contrastive sets are used as the raw data of adversarial training and the test data of the pilot experiment. Then, adversarial training is used to get contrastive features according to the training target. The acquisition of contrastive features can improve extraction precision. Experimental results on the benchmark emotion cause corpus show our method outperforms the state-of-the-art method by over 12.49%, as well as demonstrates the strong robustness of CL-ECPE.http://dx.doi.org/10.1080/09540091.2022.2082383contrastive learningemotion causeadversarial samplesecpe
spellingShingle Shunxiang Zhang
Houyue Wu
Xin Xu
Guangli Zhu
Meng-Yen Hsieh
CL-ECPE: contrastive learning with adversarial samples for emotion-cause pair extraction
Connection Science
contrastive learning
emotion cause
adversarial samples
ecpe
title CL-ECPE: contrastive learning with adversarial samples for emotion-cause pair extraction
title_full CL-ECPE: contrastive learning with adversarial samples for emotion-cause pair extraction
title_fullStr CL-ECPE: contrastive learning with adversarial samples for emotion-cause pair extraction
title_full_unstemmed CL-ECPE: contrastive learning with adversarial samples for emotion-cause pair extraction
title_short CL-ECPE: contrastive learning with adversarial samples for emotion-cause pair extraction
title_sort cl ecpe contrastive learning with adversarial samples for emotion cause pair extraction
topic contrastive learning
emotion cause
adversarial samples
ecpe
url http://dx.doi.org/10.1080/09540091.2022.2082383
work_keys_str_mv AT shunxiangzhang clecpecontrastivelearningwithadversarialsamplesforemotioncausepairextraction
AT houyuewu clecpecontrastivelearningwithadversarialsamplesforemotioncausepairextraction
AT xinxu clecpecontrastivelearningwithadversarialsamplesforemotioncausepairextraction
AT guanglizhu clecpecontrastivelearningwithadversarialsamplesforemotioncausepairextraction
AT mengyenhsieh clecpecontrastivelearningwithadversarialsamplesforemotioncausepairextraction