2019/04/04 by Robin Jia, Cliff Wong, Jia, Robin +3 · 13 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Mathematics · #Artificial intelligence #Binary relation #Biomedical Text Mining and Ontologies #Computer science #Data mining #Focus (optics) #Hierarchy #Information extraction #Information retrieval #Linguistics #Matching (statistics) #Mathematics #Natural Language Processing Techniques #Natural language processing #Precision and recall #Reading (process) #Recall #Relation (database) #Relationship extraction #Representation (politics) #Sentence #Topic Modeling #Word (group theory) #cs.CL
paper · pdf · doi:10.48550/arxiv.1904.02347
published in arXiv (Cornell University) (Cornell University) · NAACL 2019
openalex publication_date 2019/04/04 · openalex created_date 2019/04/11 · arxiv created 2019/06/26 · arxiv updated 2019/06/28 · openalex updated_date 2026/08/05
Most information extraction methods focus on binary relations expressed within single sentences. In high-value domains, however, n-ary relations are of great demand (e.g., drug-gene-mutation interactions in precision oncology). Such relations often involve entity mentions that are far apart in the document, yet existing work on cross-sentence relation extraction is generally confined to small text spans (e.g., three consecutive sentences), which severely limits recall. In this paper, we propose a novel multiscale neural architecture for document-level n-ary relation extraction. Our system combines representations learned over various text spans throughout the document and across the subrelation hierarchy. Widening the system's purview to the entire document maximizes potential recall. Moreover, by integrating weak signals across the document, multiscale modeling increases precision, even in the presence of noisy labels from distant supervision. Experiments on biomedical machine reading show that our approach substantially outperforms previous n-ary relation extraction methods.