Visible to the public Document-Level Biomedical Relation Extraction with Generative Adversarial Network and Dual-Attention Multi-Instance Learning

TitleDocument-Level Biomedical Relation Extraction with Generative Adversarial Network and Dual-Attention Multi-Instance Learning
Publication TypeConference Paper
Year of Publication2021
AuthorsLi, Lishuang, Lian, Ruiyuan, Lu, Hongbin
Conference Name2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)
KeywordsBioinformatics, Biological system modeling, Conferences, dams, Document-level Relation Extraction, Dual-Attention Multi-Instance Learning, Generative Adversarial Learning, generative adversarial network, generative adversarial networks, Metrics, pubcrawl, resilience, Resiliency, Scalability, Semantics, text mining
AbstractDocument-level relation extraction (RE) aims to extract relations among entities within a document, which is more complex than its sentence-level counterpart, especially in biomedical text mining. Chemical-disease relation (CDR) extraction aims to extract complex semantic relationships between chemicals and diseases entities in documents. In order to identify the relations within and across multiple sentences at the same time, existing methods try to build different document-level heterogeneous graph. However, the entity relation representations captured by these models do not make full use of the document information and disregard the noise introduced in the process of integrating various information. In this paper, we propose a novel model DAM-GAN to document-level biomedical RE, which can extract entity-level and mention-level representations of relation instances with R-GCN and Dual-Attention Multi-Instance Learning (DAM) respectively, and eliminate the noise with Generative Adversarial Network (GAN). Entity-level representations of relation instances model the semantic information of all entity pairs from the perspective of the whole document, while the mention-level representations from the perspective of mention pairs related to these entity pairs in different sentences. Therefore, entity- and mention-level representations can be better integrated to represent relation instances. Experimental results demonstrate that our model achieves superior performance on public document-level biomedical RE dataset BioCreative V Chemical Disease Relation(CDR).
DOI10.1109/BIBM52615.2021.9669590
Citation Keyli_document-level_2021