Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2405.17900 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909212088467456 |
|---|---|
| author | Shi, Haoxiang Zhang, Xulong Cheng, Ning Zhang, Yong Yu, Jun Xiao, Jing Wang, Jianzong |
| author_facet | Shi, Haoxiang Zhang, Xulong Cheng, Ning Zhang, Yong Yu, Jun Xiao, Jing Wang, Jianzong |
| contents | The purpose of emotion recognition in conversation (ERC) is to identify the emotion category of an utterance based on contextual information. Previous ERC methods relied on simple connections for cross-modal fusion and ignored the information differences between modalities, resulting in the model being unable to focus on modality-specific emotional information. At the same time, the shared information between modalities was not processed to generate emotions. Information redundancy problem. To overcome these limitations, we propose a cross-modal fusion emotion prediction network based on vector connections. The network mainly includes two stages: the multi-modal feature fusion stage based on connection vectors and the emotion classification stage based on fused features. Furthermore, we design a supervised inter-class contrastive learning module based on emotion labels. Experimental results confirm the effectiveness of the proposed method, demonstrating excellent performance on the IEMOCAP and MELD datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_17900 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhancing Emotion Recognition in Conversation through Emotional Cross-Modal Fusion and Inter-class Contrastive Learning Shi, Haoxiang Zhang, Xulong Cheng, Ning Zhang, Yong Yu, Jun Xiao, Jing Wang, Jianzong Computation and Language The purpose of emotion recognition in conversation (ERC) is to identify the emotion category of an utterance based on contextual information. Previous ERC methods relied on simple connections for cross-modal fusion and ignored the information differences between modalities, resulting in the model being unable to focus on modality-specific emotional information. At the same time, the shared information between modalities was not processed to generate emotions. Information redundancy problem. To overcome these limitations, we propose a cross-modal fusion emotion prediction network based on vector connections. The network mainly includes two stages: the multi-modal feature fusion stage based on connection vectors and the emotion classification stage based on fused features. Furthermore, we design a supervised inter-class contrastive learning module based on emotion labels. Experimental results confirm the effectiveness of the proposed method, demonstrating excellent performance on the IEMOCAP and MELD datasets. |
| title | Enhancing Emotion Recognition in Conversation through Emotional Cross-Modal Fusion and Inter-class Contrastive Learning |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2405.17900 |