Bio-RFX: Refining Biomedical Extraction via Advanced Relation Classification and Structural Constraints
Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Keywords: Named Entity Recognition, Relation Extraction, Biomedical Literature
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
TL;DR: We propose a novel biomedical entity and relation extraction method, Bio-RFX, by classifying fine-grained relations at sentence level and exploiting the strong structural constraints for relation triplets in the textual corpus.
Abstract: The ever-growing biomedical publications magnify the challenge of extracting structured data from unstructured texts. This task involves two components: biomedical entity identification (Named Entity Recognition) and their interrelation determination (Relation Extraction). However, pre-existing methods often neglect unique features of the biomedical literature, such as ambiguous entities, nested proper nouns, and overlapping relation triplets, and underutilize prior knowledge, leading to an intolerable performance decline in the biomedical domain, especially with limited annotated training data. In this paper, we propose the **Bio**medical **R**elation-**F**irst E**X**traction (Bio-RFX) model by leveraging sentence-level relation classification before entity extraction to tackle entity ambiguity. Moreover, we exploit structural constraints between entities and relations to guide the model's hypothesis space, enhancing extraction performance across different training scenarios. Comprehensive experiments on multiple biomedical datasets show that Bio-RFX achieves significant improvements on both named entity recognition and relation extraction tasks, especially under low-resource training scenarios, achieving a remarkable **5.13%** absolute improvement on average in NER, and **7.20%** absolute improvement on average in RE compared to baselines. The source code and pertinent documentation are readily accessible on established open-source repositories.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 7188
Loading