Similarity-based Memory Enhanced Joint Entity and Relation Extraction
This addresses the challenge of complex inter-task dependencies in information extraction for biomedical domains, though it is incremental.
The paper tackles document-level joint entity and relation extraction by proposing a multi-task learning framework with bidirectional memory-like dependencies between tasks, achieving state-of-the-art results on the BioCreative V CDR corpus.
Document-level joint entity and relation extraction is a challenging information extraction problem that requires a unified approach where a single neural network performs four sub-tasks: mention detection, coreference resolution, entity classification, and relation extraction. Existing methods often utilize a sequential multi-task learning approach, in which the arbitral decomposition causes the current task to depend only on the previous one, missing the possible existence of the more complex relationships between them. In this paper, we present a multi-task learning framework with bidirectional memory-like dependency between tasks to address those drawbacks and perform the joint problem more accurately. Our empirical studies show that the proposed approach outperforms the existing methods and achieves state-of-the-art results on the BioCreative V CDR corpus.