Knowledge-augmented Pre-trained Language Models for Biomedical Relation Extraction
This work addresses the challenge of inconsistent comparisons in biomedical relation extraction, offering insights for researchers in bioinformatics, but it is incremental as it builds on existing methods with minor gains.
The study evaluated pre-trained language models enhanced with contextual information for biomedical relation extraction across five datasets, finding that model choice and hyperparameter optimization are crucial for performance, while context information provided only minor overall improvements but substantial benefits for smaller models.
Automatic relationship extraction (RE) from biomedical literature is critical for managing the vast amount of scientific knowledge produced each year. In recent years, utilizing pre-trained language models (PLMs) has become the prevalent approach in RE. Several studies report improved performance when incorporating additional context information while fine-tuning PLMs for RE. However, variations in the PLMs applied, the databases used for augmentation, hyper-parameter optimization, and evaluation methods complicate direct comparisons between studies and raise questions about the generalizability of these findings. Our study addresses this research gap by evaluating PLMs enhanced with contextual information on five datasets spanning four relation scenarios within a consistent evaluation framework. We evaluate three baseline PLMs and first conduct extensive hyperparameter optimization. After selecting the top-performing model, we enhance it with additional data, including textual entity descriptions, relational information from knowledge graphs, and molecular structure encodings. Our findings illustrate the importance of i) the choice of the underlying language model and ii) a comprehensive hyperparameter optimization for achieving strong extraction performance. Although inclusion of context information yield only minor overall improvements, an ablation study reveals substantial benefits for smaller PLMs when such external data was included during fine-tuning.