Chinese Relation Classification using Long Short Term Memory Networks

Relation classification is the task to predict semantic relations between pairs of entities in a given text. In this paper, a novel Long Short Term Memory Network (LSTM)-based approach is proposed to extract relations between entities in Chinese text. The shortest dependency path (SDP) between two entities, together with the various selected features in the path, are first extracted, and then used as input of an LSTM model to predict the relation between them. The performance of the system was evaluated on the ACE 2005 Multilingual Training Corpus (Walker et al., 2006), and achieved a state-of-the-art F-measure of 87.87% on six general type relations and 83.40% on eighteen subtype relations in this corpus.

[1]  Aric Hagberg,et al.  Exploring Network Structure, Dynamics, and Function using NetworkX , 2008, Proceedings of the Python in Science Conference.

[2]  Qinghua Zheng,et al.  Omni-word Feature and Soft Constraint for Chinese Relation Extraction , 2014, ACL.

[3]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[4]  Dan I. Moldovan,et al.  Polaris: Lymba's Semantic Parser , 2012, LREC.

[5]  Aron Culotta,et al.  Dependency Tree Kernels for Relation Extraction , 2004, ACL.

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

[7]  Liu Dandan,et al.  Exploiting Lexical Semantic Resource for Tree Kernel-Based Chinese Relation Extraction , 2012 .

[8]  Danqi Chen,et al.  A Fast and Accurate Dependency Parser using Neural Networks , 2014, EMNLP.

[9]  Andrew Y. Ng,et al.  Semantic Compositionality through Recursive Matrix-Vector Spaces , 2012, EMNLP.

[10]  Furu Wei,et al.  Exploiting the Role of Position Feature in Chinese Relation Extraction , 2008, LREC.

[11]  Dmitry Zelenko,et al.  Kernel Methods for Relation Extraction , 2002, J. Mach. Learn. Res..

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

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

[14]  Nitish Srivastava,et al.  Improving neural networks by preventing co-adaptation of feature detectors , 2012, ArXiv.

[15]  Alessandro Moschitti,et al.  Embedding Semantic Similarity in Tree Kernels for Domain Adaptation of Relation Extraction , 2013, ACL.

[16]  ChengXiang Zhai,et al.  A Systematic Exploration of the Feature Space for Relation Extraction , 2007, NAACL.

[17]  Jian Su,et al.  A Composite Kernel to Extract Relations between Entities with Both Flat and Structured Features , 2006, ACL.

[18]  Mihai Surdeanu,et al.  The Stanford CoreNLP Natural Language Processing Toolkit , 2014, ACL.

[19]  Razvan C. Bunescu,et al.  A Shortest Path Dependency Kernel for Relation Extraction , 2005, HLT.

[20]  Wanxiang Che,et al.  Improved-Edit-Distance Kernel for Chinese Relation Extraction , 2005, IJCNLP.

[21]  Roger Levy,et al.  Is it Harder to Parse Chinese, or the Chinese Treebank? , 2003, ACL.

[22]  Dawei Song,et al.  Developing Position Structure-Based Framework for Chinese Entity Relation Extraction , 2011, TALIP.

[23]  Jinxiu Chen,et al.  Research on mixed model-based Chinese relation extraction , 2010, 2010 3rd International Conference on Computer Science and Information Technology.

[24]  Zhi Jin,et al.  Classifying Relations via Long Short Term Memory Networks along Shortest Dependency Paths , 2015, EMNLP.

[25]  Furu Wei,et al.  A Novel Feature-based Approach to Chinese Entity Relation Extraction , 2008, ACL.

[26]  Jun Zhao,et al.  Relation Classification via Convolutional Deep Neural Network , 2014, COLING.

[27]  Dejing Dou,et al.  Chain Based RNN for Relation Classification , 2015, NAACL.

[28]  Jian Su,et al.  Exploring Various Knowledge in Relation Extraction , 2005, ACL.

[29]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[30]  Chen Yu,et al.  Chinese Relation Extraction Based on Deep Belief Nets , 2012 .

[31]  Ralph Grishman,et al.  Relation Extraction: Perspective from Convolutional Neural Networks , 2015, VS@HLT-NAACL.

[32]  Guodong Zhou,et al.  Tree Kernel-Based Relation Extraction with Context-Sensitive Structured Parse Tree Information , 2007, EMNLP.

[33]  Mengqiu Wang,et al.  A Re-examination of Dependency Path Kernels for Relation Extraction , 2008, IJCNLP.

[34]  Le Sun,et al.  Study of Kernel-Based Methods for Chinese Relation Extraction , 2008, AIRS.

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

[36]  Liu Lei,et al.  Implementation of a Kernel-Based Chinese Relation Extraction System , 2007 .

[37]  Zhu Qiaoming.  Chinese Semantic Relation Extraction Based on Unified Syntactic and Entity Semantic Tree , 2010 .

[38]  Nanda Kambhatla,et al.  Combining Lexical, Syntactic, and Semantic Features with Maximum Entropy Models for Information Extraction , 2004, ACL.