Knowledge‐enriched joint‐learning model for implicit emotion cause extraction
Abstract Emotion cause extraction (ECE) task that aims at extracting potential trigger events of certain emotions has attracted extensive attention recently. However, current work neglects the implicit emotion expressed without any explicit emotional keywords, which appears more frequently in applic...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-03-01
|
| Series: | CAAI Transactions on Intelligence Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/cit2.12099 |
| _version_ | 1827990616843223040 |
|---|---|
| author | Chenghao Wu Shumin Shi Jiaxing Hu Heyan Huang |
| author_facet | Chenghao Wu Shumin Shi Jiaxing Hu Heyan Huang |
| author_sort | Chenghao Wu |
| collection | DOAJ |
| description | Abstract Emotion cause extraction (ECE) task that aims at extracting potential trigger events of certain emotions has attracted extensive attention recently. However, current work neglects the implicit emotion expressed without any explicit emotional keywords, which appears more frequently in application scenarios. The lack of explicit emotion information makes it extremely hard to extract emotion causes only with the local context. Moreover, an entire event is usually across multiple clauses, while existing work merely extracts cause events at clause level and cannot effectively capture complete cause event information. To address these issues, the events are first redefined at the tuple level and a span‐based tuple‐level algorithm is proposed to extract events from different clauses. Based on it, a corpus for implicit emotion cause extraction that tries to extract causes of implicit emotions is constructed. The authors propose a knowledge‐enriched joint‐learning model of implicit emotion recognition and implicit emotion cause extraction tasks (KJ‐IECE), which leverages commonsense knowledge from ConceptNet and NRC_VAD to better capture connections between emotion and corresponding cause events. Experiments on both implicit and explicit emotion cause extraction datasets demonstrate the effectiveness of the proposed model. |
| first_indexed | 2024-04-10T00:38:09Z |
| format | Article |
| id | doaj.art-1a6e72af509a4f84ba92d8fa88e0ca00 |
| institution | Directory Open Access Journal |
| issn | 2468-2322 |
| language | English |
| last_indexed | 2024-04-10T00:38:09Z |
| publishDate | 2023-03-01 |
| publisher | Wiley |
| record_format | Article |
| series | CAAI Transactions on Intelligence Technology |
| spelling | doaj.art-1a6e72af509a4f84ba92d8fa88e0ca002023-03-14T08:04:43ZengWileyCAAI Transactions on Intelligence Technology2468-23222023-03-018111812810.1049/cit2.12099Knowledge‐enriched joint‐learning model for implicit emotion cause extractionChenghao Wu0Shumin Shi1Jiaxing Hu2Heyan Huang3School of Computer Science and Technology Beijing Institute of Technology Beijing ChinaSchool of Computer Science and Technology Beijing Institute of Technology Beijing ChinaSchool of Computer Science and Technology Beijing Institute of Technology Beijing ChinaSchool of Computer Science and Technology Beijing Institute of Technology Beijing ChinaAbstract Emotion cause extraction (ECE) task that aims at extracting potential trigger events of certain emotions has attracted extensive attention recently. However, current work neglects the implicit emotion expressed without any explicit emotional keywords, which appears more frequently in application scenarios. The lack of explicit emotion information makes it extremely hard to extract emotion causes only with the local context. Moreover, an entire event is usually across multiple clauses, while existing work merely extracts cause events at clause level and cannot effectively capture complete cause event information. To address these issues, the events are first redefined at the tuple level and a span‐based tuple‐level algorithm is proposed to extract events from different clauses. Based on it, a corpus for implicit emotion cause extraction that tries to extract causes of implicit emotions is constructed. The authors propose a knowledge‐enriched joint‐learning model of implicit emotion recognition and implicit emotion cause extraction tasks (KJ‐IECE), which leverages commonsense knowledge from ConceptNet and NRC_VAD to better capture connections between emotion and corresponding cause events. Experiments on both implicit and explicit emotion cause extraction datasets demonstrate the effectiveness of the proposed model.https://doi.org/10.1049/cit2.12099emotion cause extractionexternal knowledge fusionimplicit emotion recognitionjoint learning |
| spellingShingle | Chenghao Wu Shumin Shi Jiaxing Hu Heyan Huang Knowledge‐enriched joint‐learning model for implicit emotion cause extraction CAAI Transactions on Intelligence Technology emotion cause extraction external knowledge fusion implicit emotion recognition joint learning |
| title | Knowledge‐enriched joint‐learning model for implicit emotion cause extraction |
| title_full | Knowledge‐enriched joint‐learning model for implicit emotion cause extraction |
| title_fullStr | Knowledge‐enriched joint‐learning model for implicit emotion cause extraction |
| title_full_unstemmed | Knowledge‐enriched joint‐learning model for implicit emotion cause extraction |
| title_short | Knowledge‐enriched joint‐learning model for implicit emotion cause extraction |
| title_sort | knowledge enriched joint learning model for implicit emotion cause extraction |
| topic | emotion cause extraction external knowledge fusion implicit emotion recognition joint learning |
| url | https://doi.org/10.1049/cit2.12099 |
| work_keys_str_mv | AT chenghaowu knowledgeenrichedjointlearningmodelforimplicitemotioncauseextraction AT shuminshi knowledgeenrichedjointlearningmodelforimplicitemotioncauseextraction AT jiaxinghu knowledgeenrichedjointlearningmodelforimplicitemotioncauseextraction AT heyanhuang knowledgeenrichedjointlearningmodelforimplicitemotioncauseextraction |