Abstract
In this paper, we propose a recurrent neural network model for identifying protein-protein interactions in biomedical literature. Experiments on two largest public benchmark datasets, AIMed and BioInfer, demonstrate that our approach significantly surpasses state-of-the-art methods with relative improvements of 10% and 18%, respectively. Cross-corpus evaluation also demonstrate that the proposed model remains robust despite using different training data. These results suggest that RNN can effectively capture semantic relationships among proteins as well as generalizes over different corpora, without any feature engineering.- Anthology ID:
- I17-2041
- Volume:
- Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
- Month:
- November
- Year:
- 2017
- Address:
- Taipei, Taiwan
- Editors:
- Greg Kondrak, Taro Watanabe
- Venue:
- IJCNLP
- SIG:
- Publisher:
- Asian Federation of Natural Language Processing
- Note:
- Pages:
- 240–245
- Language:
- URL:
- https://aclanthology.org/I17-2041
- DOI:
- Cite (ACL):
- Yu-Lun Hsieh, Yung-Chun Chang, Nai-Wen Chang, and Wen-Lian Hsu. 2017. Identifying Protein-protein Interactions in Biomedical Literature using Recurrent Neural Networks with Long Short-Term Memory. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 240–245, Taipei, Taiwan. Asian Federation of Natural Language Processing.
- Cite (Informal):
- Identifying Protein-protein Interactions in Biomedical Literature using Recurrent Neural Networks with Long Short-Term Memory (Hsieh et al., IJCNLP 2017)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/I17-2041.pdf