Abstract
We investigate the incorporation of character-based word representations into a standard CNN-based relation extraction model. We experiment with two common neural architectures, CNN and LSTM, to learn word vector representations from character embeddings. Through a task on the BioCreative-V CDR corpus, extracting relationships between chemicals and diseases, we show that models exploiting the character-based word representations improve on models that do not use this information, obtaining state-of-the-art result relative to previous neural approaches.- Anthology ID:
- W18-2314
- Volume:
- Proceedings of the BioNLP 2018 workshop
- Month:
- July
- Year:
- 2018
- Address:
- Melbourne, Australia
- Editors:
- Dina Demner-Fushman, Kevin Bretonnel Cohen, Sophia Ananiadou, Junichi Tsujii
- Venue:
- BioNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 129–136
- Language:
- URL:
- https://aclanthology.org/W18-2314
- DOI:
- 10.18653/v1/W18-2314
- Cite (ACL):
- Dat Quoc Nguyen and Karin Verspoor. 2018. Convolutional neural networks for chemical-disease relation extraction are improved with character-based word embeddings. In Proceedings of the BioNLP 2018 workshop, pages 129–136, Melbourne, Australia. Association for Computational Linguistics.
- Cite (Informal):
- Convolutional neural networks for chemical-disease relation extraction are improved with character-based word embeddings (Nguyen & Verspoor, BioNLP 2018)
- PDF:
- https://preview.aclanthology.org/naacl24-info/W18-2314.pdf