Exploring Deep Belief Network for Chinese Relation Extraction

Relation extraction is a fundamental task in information extraction that identifies the semantic relationships between two entities in the text. In this paper, a novel model based on Deep Belief Network (DBN) is first presented to detect and classify the relations among Chinese entities. The experiments conducted on the Automatic Content Extraction (ACE) 2004 dataset demonstrate that the proposed approach is effective in handling high dimensional feature space including character N-grams, entity types and the position information. It outperforms the stateof-the-art learning models such as SVM or BP neutral network.

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

[2]  Geoffrey E. Hinton.  Training Products of Experts by Minimizing Contrastive Divergence , 2002, Neural Computation.

[3]  Sergey Brin,et al.  Extracting Patterns and Relations from the World Wide Web , 1998, WebDB.

[4]  Ji Zhang,et al.  A Novel Composite Kernel Approach to Chinese Entity Relation Extraction , 2009, ICCPOL.

[5]  Geoffrey E. Hinton,et al.  A Learning Algorithm for Boltzmann Machines , 1985, Cogn. Sci..

[6]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[7]  Dmitry Zelenko,et al.  Kernel methods for relation extraction , 2003 .

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

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

[10]  Geoffrey E. Hinton.  Products of experts , 1999 .

[11]  Jason Weston,et al.  Large-scale kernel machines , 2007 .

[12]  Diego Mollá-Aliod,et al.  Proceedings of the 22nd International Conference on Computer Processing of Oriental Languages. Language Technology for the Knowledge-based Economy , 2009 .

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

[14]  Sun Xia,et al.  Feature-Based Approach to Chinese Term Relation Extraction , 2009, 2009 International Conference on Signal Processing Systems.

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

[16]  Dong-Hong Ji,et al.  Relation Extraction Using Label Propagation Based Semi-Supervised Learning , 2006, ACL.

[17]  Timothy Baldwin,et al.  Experiments on pattern-based relation learning , 2009, CIKM.

[18]  Yoshua Bengio,et al.  Scaling learning algorithms towards AI , 2007 .

[19]  Xiaoqiang Luo,et al.  HowtogetaChineseName(Entity): Segmentation and Combination Issues , 2003, EMNLP.

[20]  Man Lung Yiu,et al.  Group-by skyline query processing in relational engines , 2009, CIKM.