Abstract
In this paper, we describe a deep-learning system for emotion detection in textual conversations that participated in SemEval-2019 Task 3 “EmoContext”. We designed a specific architecture of bidirectional LSTM which allows not only to learn semantic and sentiment feature representation, but also to capture user-specific conversation features. To fine-tune word embeddings using distant supervision we additionally collected a significant amount of emotional texts. The system achieved 72.59% micro-average F1 score for emotion classes on the test dataset, thereby significantly outperforming the officially-released baseline. Word embeddings and the source code were released for the research community.- Anthology ID:
- S19-2034
- Volume:
- Proceedings of the 13th International Workshop on Semantic Evaluation
- Month:
- June
- Year:
- 2019
- Address:
- Minneapolis, Minnesota, USA
- Editors:
- Jonathan May, Ekaterina Shutova, Aurelie Herbelot, Xiaodan Zhu, Marianna Apidianaki, Saif M. Mohammad
- Venue:
- SemEval
- SIG:
- SIGLEX
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 210–214
- Language:
- URL:
- https://aclanthology.org/S19-2034
- DOI:
- 10.18653/v1/S19-2034
- Cite (ACL):
- Sergey Smetanin. 2019. EmoSense at SemEval-2019 Task 3: Bidirectional LSTM Network for Contextual Emotion Detection in Textual Conversations. In Proceedings of the 13th International Workshop on Semantic Evaluation, pages 210–214, Minneapolis, Minnesota, USA. Association for Computational Linguistics.
- Cite (Informal):
- EmoSense at SemEval-2019 Task 3: Bidirectional LSTM Network for Contextual Emotion Detection in Textual Conversations (Smetanin, SemEval 2019)
- PDF:
- https://preview.aclanthology.org/emnlp22-frontmatter/S19-2034.pdf
- Code
- sismetanin/emosense-semeval2019-task3-emocontext
- Data
- EmoContext