Abstract
This paper describes the systems developed by IRISA to participate to the four tasks of the SMM4H 2018 challenge. For these tweet classification tasks, we adopt a common approach based on recurrent neural networks (BiLSTM). Our main contributions are the use of certain features, the use of Bagging in order to deal with unbalanced datasets, and on the automatic selection of difficult examples. These techniques allow us to reach 91.4, 46.5, 47.8, 85.0 as F1-scores for Tasks 1 to 4.- Anthology ID:
- W18-5913
- Volume:
- Proceedings of the 2018 EMNLP Workshop SMM4H: The 3rd Social Media Mining for Health Applications Workshop & Shared Task
- Month:
- October
- Year:
- 2018
- Address:
- Brussels, Belgium
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 50–51
- Language:
- URL:
- https://aclanthology.org/W18-5913
- DOI:
- 10.18653/v1/W18-5913
- Cite (ACL):
- Anne-Lyse Minard, Christian Raymond, and Vincent Claveau. 2018. IRISA at SMM4H 2018: Neural Network and Bagging for Tweet Classification. In Proceedings of the 2018 EMNLP Workshop SMM4H: The 3rd Social Media Mining for Health Applications Workshop & Shared Task, pages 50–51, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- IRISA at SMM4H 2018: Neural Network and Bagging for Tweet Classification (Minard et al., EMNLP 2018)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/W18-5913.pdf