An Emotion Type Informed Multi-Task Model for Emotion Cause Pair Extraction
Emotion-Cause Pair Extraction (ECPE) aims to jointly extract emotion clauses and the corresponding cause clauses from a document, which is important for user evaluation or public opinion analysis. Existing research addresses the ECPE task through a two-step or an end-to-end approach. Although previo...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10413477/ |
| _version_ | 1797335539794313216 |
|---|---|
| author | Zhe Chen Ming Zhang Vasile Palade Liya Wang Junchi Zhang Ying Feng |
| author_facet | Zhe Chen Ming Zhang Vasile Palade Liya Wang Junchi Zhang Ying Feng |
| author_sort | Zhe Chen |
| collection | DOAJ |
| description | Emotion-Cause Pair Extraction (ECPE) aims to jointly extract emotion clauses and the corresponding cause clauses from a document, which is important for user evaluation or public opinion analysis. Existing research addresses the ECPE task through a two-step or an end-to-end approach. Although previous work shows promising performances, they suffer from two limitations: 1) they fail to take full advantage of emotion type information, which has advantages for modelling the dependencies between emotion and cause clauses from a semantic perspective; 2) they ignored the interaction between local and global information, which is important for ECPE. To address these issues, we propose an ECPE Pair Generator (ECPE-PG), with a Clause-Encoder layer, a Pre-Output layer and an Information Interaction-based Pair Generation (IIPG) Module embedded. This model first encodes clauses into vector representations through the Clause-Encoder layer and then preforms emotion clause extraction (EE), cause clause extraction (CE) and emotion type extraction (ETE), respectively, through the Pre-Output layer, on the basis of which the IIPG module analyzes the complex emotional logic of relationships between clauses and estimates the candidate pairs based on the interaction of global and local information. It should be noted that emotion type information is regarded as a crucial indication in the IIPG module to assist the identification of emotion-cause pairs. Experimental results show that our method outperforms the state-of-the-art methods on benchmark datasets. |
| first_indexed | 2024-03-08T08:39:53Z |
| format | Article |
| id | doaj.art-f7f4f22cb69b4c7e8440767c47c03233 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-08T08:39:53Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-f7f4f22cb69b4c7e8440767c47c032332024-02-02T00:02:20ZengIEEEIEEE Access2169-35362024-01-0112156621567410.1109/ACCESS.2024.335798210413477An Emotion Type Informed Multi-Task Model for Emotion Cause Pair ExtractionZhe Chen0Ming Zhang1https://orcid.org/0000-0003-4145-5389Vasile Palade2https://orcid.org/0000-0002-6768-8394Liya Wang3Junchi Zhang4https://orcid.org/0000-0001-7701-568XYing Feng5Hubei Provincial Key Laboratory of Intelligent Robot, School of Computer Science and Engineering, School of Artificial Intelligence, Wuhan Institute of Technology, Wuhan, ChinaHubei Provincial Key Laboratory of Intelligent Robot, School of Computer Science and Engineering, School of Artificial Intelligence, Wuhan Institute of Technology, Wuhan, ChinaCentre for Computational Science and Mathematical Modelling, Coventry University, Coventry, U.K.Zhejiang Industry and Trade Vocational College, Wenzhou, ChinaJianghan University, Wuhan, ChinaWuhan Institute of Technology, Wuhan, ChinaEmotion-Cause Pair Extraction (ECPE) aims to jointly extract emotion clauses and the corresponding cause clauses from a document, which is important for user evaluation or public opinion analysis. Existing research addresses the ECPE task through a two-step or an end-to-end approach. Although previous work shows promising performances, they suffer from two limitations: 1) they fail to take full advantage of emotion type information, which has advantages for modelling the dependencies between emotion and cause clauses from a semantic perspective; 2) they ignored the interaction between local and global information, which is important for ECPE. To address these issues, we propose an ECPE Pair Generator (ECPE-PG), with a Clause-Encoder layer, a Pre-Output layer and an Information Interaction-based Pair Generation (IIPG) Module embedded. This model first encodes clauses into vector representations through the Clause-Encoder layer and then preforms emotion clause extraction (EE), cause clause extraction (CE) and emotion type extraction (ETE), respectively, through the Pre-Output layer, on the basis of which the IIPG module analyzes the complex emotional logic of relationships between clauses and estimates the candidate pairs based on the interaction of global and local information. It should be noted that emotion type information is regarded as a crucial indication in the IIPG module to assist the identification of emotion-cause pairs. Experimental results show that our method outperforms the state-of-the-art methods on benchmark datasets.https://ieeexplore.ieee.org/document/10413477/Emotion cause pair extractionemotion type extractionemotion clause extractioncause clause extractionglobal informationlocal information |
| spellingShingle | Zhe Chen Ming Zhang Vasile Palade Liya Wang Junchi Zhang Ying Feng An Emotion Type Informed Multi-Task Model for Emotion Cause Pair Extraction IEEE Access Emotion cause pair extraction emotion type extraction emotion clause extraction cause clause extraction global information local information |
| title | An Emotion Type Informed Multi-Task Model for Emotion Cause Pair Extraction |
| title_full | An Emotion Type Informed Multi-Task Model for Emotion Cause Pair Extraction |
| title_fullStr | An Emotion Type Informed Multi-Task Model for Emotion Cause Pair Extraction |
| title_full_unstemmed | An Emotion Type Informed Multi-Task Model for Emotion Cause Pair Extraction |
| title_short | An Emotion Type Informed Multi-Task Model for Emotion Cause Pair Extraction |
| title_sort | emotion type informed multi task model for emotion cause pair extraction |
| topic | Emotion cause pair extraction emotion type extraction emotion clause extraction cause clause extraction global information local information |
| url | https://ieeexplore.ieee.org/document/10413477/ |
| work_keys_str_mv | AT zhechen anemotiontypeinformedmultitaskmodelforemotioncausepairextraction AT mingzhang anemotiontypeinformedmultitaskmodelforemotioncausepairextraction AT vasilepalade anemotiontypeinformedmultitaskmodelforemotioncausepairextraction AT liyawang anemotiontypeinformedmultitaskmodelforemotioncausepairextraction AT junchizhang anemotiontypeinformedmultitaskmodelforemotioncausepairextraction AT yingfeng anemotiontypeinformedmultitaskmodelforemotioncausepairextraction AT zhechen emotiontypeinformedmultitaskmodelforemotioncausepairextraction AT mingzhang emotiontypeinformedmultitaskmodelforemotioncausepairextraction AT vasilepalade emotiontypeinformedmultitaskmodelforemotioncausepairextraction AT liyawang emotiontypeinformedmultitaskmodelforemotioncausepairextraction AT junchizhang emotiontypeinformedmultitaskmodelforemotioncausepairextraction AT yingfeng emotiontypeinformedmultitaskmodelforemotioncausepairextraction |