Exploiting sequence labeling framework to extract document-level relations from biomedical texts

• Published in: BMC bioinformatics Vol. 21; no. 1; p. 125
• Main Authors: Li, Zhiheng, Yang, Zhihao, Xiang, Yang, Luo, Ling, Sun, Yuanyuan, Lin, Hongfei
• Format: Journal Article
• Language: English
• Published: England BioMed Central Ltd 27-03-2020; BioMed Central; BMC
• Subjects: Annotations; Biomedical Research; Classification; Data mining; Data Mining - methods; Design; Document-level relation; Electronic health records; Feature extraction; Insulin resistance; Labeling; Medical research; Methodology; Methods; Relation extraction; Semantics; Sequence labeling; Texts; Relation extraction; Document-level relation; Sequence labeling
• ISSN: 1471-2105; 1471-2105
• DOI: 10.1186/s12859-020-3457-2

Both intra- and inter-sentential semantic relations in biomedical texts provide valuable information for biomedical research. However, most existing methods either focus on extracting intra-sentential relations and ignore inter-sentential ones or fail to extract inter-sentential relations accurately and regard the instances containing entity relations as being independent, which neglects the interactions between relations. We propose a novel sequence labeling-based biomedical relation extraction method named Bio-Seq. In the method, sequence labeling framework is extended by multiple specified feature extractors so as to facilitate the feature extractions at different levels, especially at the inter-sentential level. Besides, the sequence labeling framework enables Bio-Seq to take advantage of the interactions between relations, and thus, further improves the precision of document-level relation extraction.
Our proposed method obtained an F1-score of 63.5% on BioCreative V chemical disease relation corpus, and an F1-score of 54.4% on inter-sentential relations, which was 10.5% better than the document-level classification baseline. Also, our method achieved an F1-score of 85.1% on n2c2-ADE sub-dataset.
Sequence labeling method can be successfully used to extract document-level relations, especially for boosting the performance on inter-sentential relation extraction. Our work can facilitate the research on document-level biomedical text mining.