Deep Neural Networks Based on Span Association Prediction for Emotion-Cause Pair Extraction
The emotion-cause pair extraction task is a fine-grained task in text sentiment analysis, which aims to extract all emotions and their underlying causes in a document. Recent studies have addressed the emotion-cause pair extraction task in a step-by-step manner, i.e., the two subtasks of emotion ext...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/10/3637 |
| _version_ | 1797495805747134464 |
|---|---|
| author | Weichun Huang Yixue Yang Zhiying Peng Liyan Xiong Xiaohui Huang |
| author_facet | Weichun Huang Yixue Yang Zhiying Peng Liyan Xiong Xiaohui Huang |
| author_sort | Weichun Huang |
| collection | DOAJ |
| description | The emotion-cause pair extraction task is a fine-grained task in text sentiment analysis, which aims to extract all emotions and their underlying causes in a document. Recent studies have addressed the emotion-cause pair extraction task in a step-by-step manner, i.e., the two subtasks of emotion extraction and cause extraction are completed first, followed by the pairing task of emotion-cause pairs. However, this fail to deal well with the potential relationship between the two subtasks and the extraction task of emotion-cause pairs. At the same time, the grammatical information contained in the document itself is ignored. To address the above issues, we propose a deep neural network based on span association prediction for the task of emotion-cause pair extraction, exploiting general grammatical conventions to span-encode sentences. We use the span association pairing method to obtain candidate emotion-cause pairs, and establish a multi-dimensional information interaction mechanism to screen candidate emotion-cause pairs. Experimental results on a quasi-baseline corpus show that our model can accurately extract potential emotion-cause pairs and outperform existing baselines. |
| first_indexed | 2024-03-10T01:54:50Z |
| format | Article |
| id | doaj.art-3e93ea8f71bb406e975e10b6d3442c7a |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T01:54:50Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-3e93ea8f71bb406e975e10b6d3442c7a2023-11-23T12:58:36ZengMDPI AGSensors1424-82202022-05-012210363710.3390/s22103637Deep Neural Networks Based on Span Association Prediction for Emotion-Cause Pair ExtractionWeichun Huang0Yixue Yang1Zhiying Peng2Liyan Xiong3Xiaohui Huang4School of Software Department, East China Jiaotong University, Nanchang 330013, ChinaSchool of Software Department, East China Jiaotong University, Nanchang 330013, ChinaSchool of Software Department, East China Jiaotong University, Nanchang 330013, ChinaSchool of Software Department, East China Jiaotong University, Nanchang 330013, ChinaSchool of Software Department, East China Jiaotong University, Nanchang 330013, ChinaThe emotion-cause pair extraction task is a fine-grained task in text sentiment analysis, which aims to extract all emotions and their underlying causes in a document. Recent studies have addressed the emotion-cause pair extraction task in a step-by-step manner, i.e., the two subtasks of emotion extraction and cause extraction are completed first, followed by the pairing task of emotion-cause pairs. However, this fail to deal well with the potential relationship between the two subtasks and the extraction task of emotion-cause pairs. At the same time, the grammatical information contained in the document itself is ignored. To address the above issues, we propose a deep neural network based on span association prediction for the task of emotion-cause pair extraction, exploiting general grammatical conventions to span-encode sentences. We use the span association pairing method to obtain candidate emotion-cause pairs, and establish a multi-dimensional information interaction mechanism to screen candidate emotion-cause pairs. Experimental results on a quasi-baseline corpus show that our model can accurately extract potential emotion-cause pairs and outperform existing baselines.https://www.mdpi.com/1424-8220/22/10/3637emotion-cause pair extractionmulti-task learningdeep neural network |
| spellingShingle | Weichun Huang Yixue Yang Zhiying Peng Liyan Xiong Xiaohui Huang Deep Neural Networks Based on Span Association Prediction for Emotion-Cause Pair Extraction Sensors emotion-cause pair extraction multi-task learning deep neural network |
| title | Deep Neural Networks Based on Span Association Prediction for Emotion-Cause Pair Extraction |
| title_full | Deep Neural Networks Based on Span Association Prediction for Emotion-Cause Pair Extraction |
| title_fullStr | Deep Neural Networks Based on Span Association Prediction for Emotion-Cause Pair Extraction |
| title_full_unstemmed | Deep Neural Networks Based on Span Association Prediction for Emotion-Cause Pair Extraction |
| title_short | Deep Neural Networks Based on Span Association Prediction for Emotion-Cause Pair Extraction |
| title_sort | deep neural networks based on span association prediction for emotion cause pair extraction |
| topic | emotion-cause pair extraction multi-task learning deep neural network |
| url | https://www.mdpi.com/1424-8220/22/10/3637 |
| work_keys_str_mv | AT weichunhuang deepneuralnetworksbasedonspanassociationpredictionforemotioncausepairextraction AT yixueyang deepneuralnetworksbasedonspanassociationpredictionforemotioncausepairextraction AT zhiyingpeng deepneuralnetworksbasedonspanassociationpredictionforemotioncausepairextraction AT liyanxiong deepneuralnetworksbasedonspanassociationpredictionforemotioncausepairextraction AT xiaohuihuang deepneuralnetworksbasedonspanassociationpredictionforemotioncausepairextraction |