BERTChem-DDI : Improved Drug-Drug Interaction Prediction from text using Chemical Structure Information

Ishani Mondal


Abstract
Traditional biomedical version of embeddings obtained from pre-trained language models have recently shown state-of-the-art results for relation extraction (RE) tasks in the medical domain. In this paper, we explore how to incorporate domain knowledge, available in the form of molecular structure of drugs, for predicting Drug-Drug Interaction from textual corpus. We propose a method, BERTChem-DDI, to efficiently combine drug embeddings obtained from the rich chemical structure of drugs (encoded in SMILES) along with off-the-shelf domain-specific BioBERT embedding-based RE architecture. Experiments conducted on the DDIExtraction 2013 corpus clearly indicate that this strategy improves other strong baselines architectures by 3.4% macro F1-score.
Anthology ID:
2020.knlp-1.4
Volume:
Proceedings of Knowledgeable NLP: the First Workshop on Integrating Structured Knowledge and Neural Networks for NLP
Month:
December
Year:
2020
Address:
Suzhou, China
Editors:
Oren Sar Shalom, Alexander Panchenko, Cicero dos Santos, Varvara Logacheva, Alessandro Moschitti, Ido Dagan
Venue:
knlp
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
27–32
Language:
URL:
https://aclanthology.org/2020.knlp-1.4
DOI:
Bibkey:
Cite (ACL):
Ishani Mondal. 2020. BERTChem-DDI : Improved Drug-Drug Interaction Prediction from text using Chemical Structure Information. In Proceedings of Knowledgeable NLP: the First Workshop on Integrating Structured Knowledge and Neural Networks for NLP, pages 27–32, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
BERTChem-DDI : Improved Drug-Drug Interaction Prediction from text using Chemical Structure Information (Mondal, knlp 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2020.knlp-1.4.pdf