Text Mining Drug/Chemical-Protein Interactions using an Ensemble of BERT and T5 Based Models
This work addresses relation extraction for biomedical text mining, but it is incremental as it applies existing models to a specific challenge task.
The paper tackled the problem of extracting drug/chemical-protein interactions from text by comparing BERT-based classification and T5-based text-to-text methods, with the BioMegatron BERT model achieving a 0.74 F1 score and the T5 method achieving 0.65 F1 score.
In Track-1 of the BioCreative VII Challenge participants are asked to identify interactions between drugs/chemicals and proteins. In-context named entity annotations for each drug/chemical and protein are provided and one of fourteen different interactions must be automatically predicted. For this relation extraction task, we attempt both a BERT-based sentence classification approach, and a more novel text-to-text approach using a T5 model. We find that larger BERT-based models perform better in general, with our BioMegatron-based model achieving the highest scores across all metrics, achieving 0.74 F1 score. Though our novel T5 text-to-text method did not perform as well as most of our BERT-based models, it outperformed those trained on similar data, showing promising results, achieving 0.65 F1 score. We believe a text-to-text approach to relation extraction has some competitive advantages and there is a lot of room for research advancement.