Chemical-protein relation extraction with ensembles of SVM, CNN, and RNN models

Text mining the relations between chemicals and proteins is an increasingly important task. The CHEMPROT track at BioCreative VI aims to promote the development and evaluation of systems that can automatically detect the chemical-protein relations in running text (PubMed abstracts). This manuscript describes our submission, which is an ensemble of three systems, including a Support Vector Machine, a Convolutional Neural Network, and a Recurrent Neural Network. Their output is combined using a decision based on majority voting or stacking. Our CHEMPROT system obtained 0.7266 in precision and 0.5735 in recall for an f-score of 0.6410, demonstrating the effectiveness of machine learning-based approaches for automatic relation extraction from biomedical literature. Our submission achieved the highest performance in the task during the 2017 challenge.

[1]  Yifan Peng,et al.  Assessing the state of the art in biomedical relation extraction: overview of the BioCreative V chemical-disease relation (CDR) task , 2016, Database J. Biol. Databases Curation.

[2]  Jihoon Yang,et al.  Data and text mining Kernel approaches for genic interaction extraction , 2008 .

[3]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[4]  Zhiyong Lu,et al.  Annotating chemicals , diseases and their interactions in biomedical literature , 2015 .

[5]  Zhiyong Lu,et al.  Mining chemical patents with an ensemble of open systems , 2016, Database J. Biol. Databases Curation.

[6]  Eugene Charniak,et al.  Any Domain Parsing: Automatic Domain Adaptation for Natural Language Parsing , 2010 .

[7]  Yifan Peng,et al.  Deep learning for extracting protein-protein interactions from biomedical literature , 2017, BioNLP.

[8]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[9]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[10]  Eugene Charniak,et al.  A Maximum-Entropy-Inspired Parser , 2000, ANLP.

[11]  Joakim Nivre,et al.  Universal Stanford dependencies: A cross-linguistic typology , 2014, LREC.

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

[13]  Jun'ichi Tsujii,et al.  Bidirectional Inference with the Easiest-First Strategy for Tagging Sequence Data , 2005, HLT.

[14]  Bowen Zhou,et al.  Classifying Relations by Ranking with Convolutional Neural Networks , 2015, ACL.

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

[16]  Tung Tran,et al.  Extracting Drug-Drug Interactions with Word and Character-Level Recurrent Neural Networks , 2017, 2017 IEEE International Conference on Healthcare Informatics (ICHI).