点击次数：

论文类型：期刊论文

发表时间：2019-07-01

发表刊物：Journal of biomedical informatics

收录刊物：PubMed、EI

卷号：95

页面范围：103221

ISSN号：1532-0480

关键字：Bi-GRU,Biomedical event trigger detection,Encoder-decoder,Gated mechanism

摘要：Biomedical events play a key role in improving biomedical research. Event trigger identification, extracting the words describing the event types, is a crucial and prerequisite step in the pipeline process of biomedical event extraction. There exist two main problems in previous methods: (1) The association among contextual trigger labels which can provide significant clues is ignored. (2)The weight between word embeddings and contextual features needs to be adjusted dynamically according to the trigger candidate. In this paper, we propose a novel contextual label sensitive gated network for biomedical event trigger extraction to solve the above two problems, which can mix the two parts dynamically and capture the contextual label clues automatically. Furthermore, we also introduce the dependency-based word embeddings to represent dependency-based semantic information as well as attention mechanism to get more focused representations. Experimental results show that our approach advances state-of-the-arts and achieves the best F1-score on the commonly used Multi-Level Event Extraction (MLEE) corpus.Copyright © 2019 Elsevier Inc. All rights reserved.