KU-MTL at SemEval-2018 Task 1: Multi-task Identification of Affect in Tweets
Thomas Nyegaard-Signori, Casper Veistrup Helms, Johannes Bjerva, Isabelle Augenstein
Abstract
We take a multi-task learning approach to the shared Task 1 at SemEval-2018. The general idea concerning the model structure is to use as little external data as possible in order to preserve the task relatedness and reduce complexity. We employ multi-task learning with hard parameter sharing to exploit the relatedness between sub-tasks. As a base model, we use a standard recurrent neural network for both the classification and regression subtasks. Our system ranks 32nd out of 48 participants with a Pearson score of 0.557 in the first subtask, and 20th out of 35 in the fifth subtask with an accuracy score of 0.464.- Anthology ID:
- S18-1058
- Volume:
- Proceedings of the 12th International Workshop on Semantic Evaluation
- Month:
- June
- Year:
- 2018
- Address:
- New Orleans, Louisiana
- Editors:
- Marianna Apidianaki, Saif M. Mohammad, Jonathan May, Ekaterina Shutova, Steven Bethard, Marine Carpuat
- Venue:
- SemEval
- SIG:
- SIGLEX
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 385–389
- Language:
- URL:
- https://aclanthology.org/S18-1058
- DOI:
- 10.18653/v1/S18-1058
- Cite (ACL):
- Thomas Nyegaard-Signori, Casper Veistrup Helms, Johannes Bjerva, and Isabelle Augenstein. 2018. KU-MTL at SemEval-2018 Task 1: Multi-task Identification of Affect in Tweets. In Proceedings of the 12th International Workshop on Semantic Evaluation, pages 385–389, New Orleans, Louisiana. Association for Computational Linguistics.
- Cite (Informal):
- KU-MTL at SemEval-2018 Task 1: Multi-task Identification of Affect in Tweets (Nyegaard-Signori et al., SemEval 2018)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-3/S18-1058.pdf