何馨宇,李丽双. 基于双向LSTM和两阶段方法的触发词识别[J]. 中文信息学报, 2017, 31(6): 147-154.
HE Xinyu, LI Lishuang. Trigger Detection Based on Bidirectional LSTM and Two-stage Method. , 2017, 31(6): 147-154.
基于双向LSTM和两阶段方法的触发词识别
何馨宇,李丽双
大连理工大学 计算机科学与技术学院,辽宁 大连 116023
Trigger Detection Based on Bidirectional LSTM and Two-stage Method
HE Xinyu, LI Lishuang
School of Computer Science and Technology, Dalian University of Technology, Dalian, Liaoning 116023, China
Abstract：The trigger detection is of significance in the biomedical event extraction. The existing trigger detection methods are almost one-stage methods based on shallow machine learning, which demands on heavy training on the rich domain knowledge and sufficient manual features. In this paper, we propose a two-stage trigger detection method based on Bidirectional Long Short Term Memory (BLSTM), which divides trigger detection into recognition stage and classification stage. This approach can relieve the issue of imbalance class effectively, and avoid the cost of manual feature extraction. In addition, to obtain more semantic information, we use the large-scale corpus downloaded from the PubMed database to train the dependency word embeddings, which effectively improves the recognition performance of trigger detection. On the multi-level event extraction (MLEE) corpus dataset, our method achieves an F-score of 78.46%, which outperforms the state-of-the-art systems.
[1]Bj?rne J.Biomedical event extraction with machine learning[J].TUCS Dissertations,2014(178):1-121. [2]Vlachos A.Two strong baselines for the BioNLP 2009 event extraction task[C]//Proceedings of the 2010 Workshop on Biomedical Natural Language Processing.Association for Computational Linguistics,2010:1-9. [3]Bjorne J,Juho H,Filip G,et al.Extracting complex biological events with rich graph-based feature sets[C]//Proceedings of the Workshop on BioNLP:Shared Task,2009:10-18. [4]Pyysalo S,Ohta T,Miwa M,et al. Event extraction across multiple levels of biological organization[J].Bioinformatics,2012,28(18):i575-i581. [5]Zhou D,Zhong D.A semi-supervised learning framework for biomedical event extraction based on hidden topics[J].Artificial Intelligence in Medicine,2015,64(1):51-58. [6]Zhou D,Zhong D,He Y.Event trigger identification for biomedical events extraction using domain knowledge[J].Bioinformatics,2014,30(11):1587-1594. [7]Wang J,Zhang J,Yuan A,et al.Biomedical event trigger detection by dependency-based word embedding[C]//Proceedings of IEEE International Conference on Bioinformatics and Biomedicine.IEEE,2015:429-432. [8]Nie Y,Rong W,Zhang Y,et al.Embedding assisted prediction architecture for event trigger identification[J].Journal of Bioinformatics & Computational Biology,2015,13(3):575-577. [9]Yoshua B,Rejean D,Pascal V,et al.A Neural Probabilistic Language Model[J].Journal of Machine Learning Research (JMLR),2003,3:1137-1155. [10]Mikolov T,Chen K,Corrado G,et al.Efficient estimation of word representations in vector space[J].2013,arXiv preprint arXiv:1301.3781. [11]Levy O,Goldberg Y.Dependency-based word embeddings[C]//Proceedings of Meeting of the Association for Computational Linguistics,2010:302-308. [12]Li L,Jin L,Jiang Y,et al.Recognizing biomedical named entities based on the sentence vector/twin word embeddings conditioned bidirectional LSTM[C]//Proceedings of China National Conference on Chinese Computational Linguistics.Springer International Publishing,2016:165-176. [13]Kolen J,Kremer S.Gradient flow in recurrent nets:the difficulty of learning long-term dependencies[M].Wiley-IEEE Press,2007,28(2):237-243. [14]Hochreiter S,Schmidhuber J.Long short-term memory[J].Neural Computation,1997,9(8):1735-1780. [15]Schuster M,Paliwal K.Bidirectional recurrent neural networks[J].Signal Processing,1997,45(11):2673-2681.
2017, Vol. 31 
