Learning Informative Representations of Biomedical Relations with Latent Variable Models
This work provides an incremental improvement in relation extraction for biomedical researchers by offering a more nuanced representation of relations.
This paper addresses the challenge of extracting biomedical relations from scientific documents by proposing a latent variable model to represent complex relations between entity pairs. The model achieves competitive results on both mention-level and pair-level relation extraction tasks, while being more parameter-efficient and faster to train than strong baselines.
Extracting biomedical relations from large corpora of scientific documents is a challenging natural language processing task. Existing approaches usually focus on identifying a relation either in a single sentence (mention-level) or across an entire corpus (pair-level). In both cases, recent methods have achieved strong results by learning a point estimate to represent the relation; this is then used as the input to a relation classifier. However, the relation expressed in text between a pair of biomedical entities is often more complex than can be captured by a point estimate. To address this issue, we propose a latent variable model with an arbitrarily flexible distribution to represent the relation between an entity pair. Additionally, our model provides a unified architecture for both mention-level and pair-level relation extraction. We demonstrate that our model achieves results competitive with strong baselines for both tasks while having fewer parameters and being significantly faster to train. We make our code publicly available.