Skip to main content Skip to main navigation


A Data-driven Approach for Noise Reduction in Distantly Supervised Biomedical Relation Extraction

Saadullah Amin; Katherine Dunfield; Anna Vechkaeva; Günter Neumann
In: BioNLP 2020 Workshop on Biomedical Natural Language Processing. Workshop on Current Trends in Biomedical Natural Language Processing (BioNLP-2020), located at The 58th Annual Meeting of the Association for Computational Linguistics, July 9, ACL, 2020.


Fact triples are a common form of structured knowledge used within the biomedical domain. As the amount of unstructured scientific texts continues to grow, manual annotation of these texts for the task of relation extraction becomes increasingly expensive. Distant supervision offers a viable approach to combat this by quickly producing large amounts of labeled, but considerably noisy, data. We aim to reduce such noise by extending an entity-enriched relation classification BERT model to the problem of multiple instance learning, and defining a simple data encoding scheme that significantly reduces noise, reaching state-of-the-art performance for distantly-supervised biomedical relation extraction. Our approach further encodes knowledge about the direction of relation triples, allowing for increased focus on relation learning by reducing noise and alleviating the need for joint learning with knowledge graph completion.


Weitere Links