Enhancing Emotion Recognition in Conversation via Multi-view Feature Alignment and Memorization
Guiyang Hou, Yongliang Shen, Wenqi Zhang, Wei Xue, Weiming Lu
Abstract
Emotion recognition in conversation (ERC) has attracted increasing attention in natural language processing community. Previous work commonly first extract semantic-view features via fine-tuning PLMs, then models context-view features based on the obtained semantic-view features by various graph neural networks. However, it is difficult to fully model interaction between utterances simply through a graph neural network and the features at semantic-view and context-view are not well aligned. Moreover, the previous parametric learning paradigm struggle to learn the patterns of tail class given fewer instances. To this end, we treat the pre-trained conversation model as a prior knowledge base and from which we elicit correlations between utterances by a probing procedure. And we adopt supervised contrastive learning to align semantic-view and context-view features, these two views of features work together in a complementary manner, contributing to ERC from distinct perspectives. Meanwhile, we propose a new semi-parametric paradigm of inferencing through memorization to solve the recognition problem of tail class samples. We consistently achieve state-of-the-art results on four widely used benchmarks. Extensive experiments demonstrate the effectiveness of our proposed multi-view feature alignment and memorization.- Anthology ID:
- 2023.findings-emnlp.842
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2023
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 12651–12663
- Language:
- URL:
- https://aclanthology.org/2023.findings-emnlp.842
- DOI:
- 10.18653/v1/2023.findings-emnlp.842
- Cite (ACL):
- Guiyang Hou, Yongliang Shen, Wenqi Zhang, Wei Xue, and Weiming Lu. 2023. Enhancing Emotion Recognition in Conversation via Multi-view Feature Alignment and Memorization. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 12651–12663, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Enhancing Emotion Recognition in Conversation via Multi-view Feature Alignment and Memorization (Hou et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/2023.findings-emnlp.842.pdf