GADGET: Using Gated GRU for Biomedical Event Trigger Detection

Biomedical event extraction plays an important role in the field of biomedical text mining, and the event trigger detection is the first step in the pipeline process of event extraction. Event trigger can clearly indicates the occurrence of related events. There have been many machine learning based methods applied to this area already. However, most previous work have omitted two crucial points: (1) Class Difference: They simply regard non-trigger as same level class label. (2) Information Isolation: Most methods only utilize token level information. In this paper, we propose a novel model based on gate mechanism, which identifies trigger and non-trigger words in the first stage. At the same time, we also introduce additional fusion layer in order to incorporate sentence level information for event trigger detection. Experimental results on the Multi Level Event Extraction (MLEE) corpus achieve superior performance than other state-of-the-art models. We have also performed ablation study to show the effectiveness of proposed model components.

[1]  Sampo Pyysalo,et al.  Event extraction across multiple levels of biological organization , 2012, Bioinform..

[2]  Guillaume Lample,et al.  Neural Architectures for Named Entity Recognition , 2016, NAACL.

[3]  Tapio Salakoski,et al.  Distributional Semantics Resources for Biomedical Text Processing , 2013 .

[4]  Andrew McCallum,et al.  Model Combination for Event Extraction in BioNLP 2011 , 2011, BioNLP@ACL.

[5]  Pierre Zweigenbaum,et al.  Overview of the Regulatory Network of Plant Seed Development (SeeDev) Task at the BioNLP Shared Task 2016. , 2016, BioNLP.

[6]  Sampo Pyysalo,et al.  Overview of BioNLP’09 Shared Task on Event Extraction , 2009, BioNLP@HLT-NAACL.

[7]  Andrew McCallum,et al.  Robust Biomedical Event Extraction with Dual Decomposition and Minimal Domain Adaptation , 2011, BioNLP@ACL.

[8]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[9]  Ted Briscoe,et al.  Biomedical Event Extraction without Training Data , 2009, BioNLP@HLT-NAACL.

[10]  Patchigolla V. S. S. Rahul,et al.  Biomedical Event Trigger Identification Using Bidirectional Recurrent Neural Network Based Models , 2017, BioNLP.

[11]  Honglei Li,et al.  Biomedical event trigger detection based on convolutional neural network , 2016, Int. J. Data Min. Bioinform..

[12]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[13]  Yang Liu,et al.  Exploiting argument information to improve biomedical event trigger identification via recurrent neural networks and supervised attention mechanisms , 2017, 2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[14]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[15]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[16]  Quang Le Minh,et al.  A Pattern Approach for Biomedical Event Annotation , 2011, Proceedings of BioNLP Shared Task 2011 Workshop.

[17]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[18]  Sophia Ananiadou,et al.  Boosting automatic event extraction from the literature using domain adaptation and coreference resolution , 2012, Bioinform..

[19]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[20]  Sampo Pyysalo,et al.  Overview of BioNLP Shared Task 2013 , 2013, BioNLP@ACL.

[21]  Deyu Zhou,et al.  Event trigger identification for biomedical events extraction using domain knowledge , 2014, Bioinform..