MedDistant19: A Challenging Benchmark for Distantly Supervised Biomedical Relation Extraction.
Proceedings of the 21st BioNLP workshop associated with the ACL SIGBIOMED 2022.
(pp. pp. 1-17).
Relation Extraction in the biomedical domain is challenging due to the lack
of labeled data and high annotation costs, needing domain experts. Distant
supervision is commonly used as a way to tackle the scarcity of annotated data
by automatically pairing knowledge graph relationships with raw texts.
Distantly Supervised Biomedical Relation Extraction (Bio-DSRE) models can
seemingly produce very accurate results in several benchmarks. However, given
the challenging nature of the task, we set out to investigate the validity of
such impressive results. We probed the datasets used by Amin et al. (2020) and
Hogan et al. (2021) and found a significant overlap between training and
evaluation relationships that, once resolved, reduced the accuracy of the
models by up to 71%. Furthermore, we noticed several inconsistencies with the
data construction process, such as creating negative samples and improper
handling of redundant relationships. We mitigate these issues and present
MedDistant19, a new benchmark dataset obtained by aligning the MEDLINE
abstracts with the widely used SNOMED Clinical Terms (SNOMED CT) knowledge
base. We experimented with several state-of-the-art models achieving an AUC of
55.4% and 49.8% at sentence- and bag-level, showing that there is still plenty
of room for improvement.
Archive Staff Only