Abstract
Emotion detection in conversations (EDC) is to detect the emotion for each utterance in conversations that have multiple speakers. Different from the traditional non-conversational emotion detection, the model for EDC should be context-sensitive (e.g., understanding the whole conversation rather than one utterance) and speaker-sensitive (e.g., understanding which utterance belongs to which speaker). In this paper, we propose a transformer-based context- and speaker-sensitive model for EDC, namely HiTrans, which consists of two hierarchical transformers. We utilize BERT as the low-level transformer to generate local utterance representations, and feed them into another high-level transformer so that utterance representations could be sensitive to the global context of the conversation. Moreover, we exploit an auxiliary task to make our model speaker-sensitive, called pairwise utterance speaker verification (PUSV), which aims to classify whether two utterances belong to the same speaker. We evaluate our model on three benchmark datasets, namely EmoryNLP, MELD and IEMOCAP. Results show that our model outperforms previous state-of-the-art models.- Anthology ID:
- 2020.coling-main.370
- Volume:
- Proceedings of the 28th International Conference on Computational Linguistics
- Month:
- December
- Year:
- 2020
- Address:
- Barcelona, Spain (Online)
- Editors:
- Donia Scott, Nuria Bel, Chengqing Zong
- Venue:
- COLING
- SIG:
- Publisher:
- International Committee on Computational Linguistics
- Note:
- Pages:
- 4190–4200
- Language:
- URL:
- https://aclanthology.org/2020.coling-main.370
- DOI:
- 10.18653/v1/2020.coling-main.370
- Cite (ACL):
- Jingye Li, Donghong Ji, Fei Li, Meishan Zhang, and Yijiang Liu. 2020. HiTrans: A Transformer-Based Context- and Speaker-Sensitive Model for Emotion Detection in Conversations. In Proceedings of the 28th International Conference on Computational Linguistics, pages 4190–4200, Barcelona, Spain (Online). International Committee on Computational Linguistics.
- Cite (Informal):
- HiTrans: A Transformer-Based Context- and Speaker-Sensitive Model for Emotion Detection in Conversations (Li et al., COLING 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2020.coling-main.370.pdf
- Data
- EmoryNLP, IEMOCAP, MELD