A relation extraction method of Chinese named entities based on location and semantic features

Named Entity Relations are a foundation of semantic networks, ontology and the semantic Web, and are widely used in information retrieval and machine translation, as well as automatic question and answering systems. Relation feature selection and extraction are two key issues. The location features possess excellent computability and operability, and the semantic features have strong intelligibility and reality. Currently, relation extraction of Chinese named entities mainly adopts the Vector Space Model (VSM) or a traditional semantic computing method, and these two methods use either the location features or the semantic features only, resulting in unsatisfactory extraction. To improve the extraction results, we propose a method that combines the information gain of the positions of words and the semantic computing based on HowNet to extract Chinese named entity relations, and present a relation extraction method of Chinese named entities, called LSE, which is scalable, semi-supervised and domain independent. Extensive experiments have been performed to show that our approach is superior, with an F-score of 0.881, which is at least 0.115 better than existing extraction methods that use either the location features or the semantic features.

[1]  Richong Zhang,et al.  An information gain-based approach for recommending useful product reviews , 2011, Knowledge and Information Systems.

[2]  Takayuki Ito,et al.  Case learning for CBR-based collision avoidance systems , 2010, Applied Intelligence.

[3]  Bing Qin,et al.  Event type recognition based on trigger expansion , 2010 .

[4]  Lu Song.  An Unsuptervised Approach to Word Sense Disambiguation Based on Sense-Words in Vector Space Model , 2002 .

[5]  Qun Liu,et al.  基於《知網》的辭彙語義相似度計算 (Word Similarity Computing Based on How-net) [In Chinese] , 2002, ROCLING/IJCLCLP.

[6]  Mohand Boughanem,et al.  Evaluation of contextual information retrieval effectiveness: overview of issues and research , 2010, Knowledge and Information Systems.

[7]  Ilyas Cicekli,et al.  A ranking method for example based machine translation results by learning from user feedback , 2011, Applied Intelligence.

[8]  Nancy Chinchor,et al.  Overview of MUC-7 , 1998, MUC.

[9]  Michael K. Ng,et al.  Knowledge-based vector space model for text clustering , 2010, Knowledge and Information Systems.

[10]  Zhao Junzhe.  Named Entity Relation Extraction Method Based on Seed Self-expansion , 2006 .

[11]  Doug Downey,et al.  A Probabilistic Model of Redundancy in Information Extraction , 2005, IJCAI.

[12]  Yongqiang Li,et al.  Improving Semantic Role Labeling with Word Sense , 2010, HLT-NAACL.

[13]  Tao Li,et al.  On combining multiple clusterings: an overview and a new perspective , 2010, Applied Intelligence.

[14]  Xing Zhang,et al.  Building a highly-compact and accurate associative classifier , 2011, Applied Intelligence.

[15]  Liu Ting,et al.  An SVMTool-Based Chinese POS Tagger , 2009 .

[16]  Enrico Motta,et al.  A hybrid approach for extracting semantic relations from texts , 2006, OntologyLearning@COLING/ACL.

[17]  Mila Ramos-Santacruz,et al.  REES: A Large-Scale Relation and Event Extraction System , 2000, ANLP.

[18]  Qun Liu,et al.  Semantic computation in a Chinese Question-Answering system , 2002, Journal of Computer Science and Technology.

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

[20]  Fabio Ciravegna,et al.  Relation Extraction for Mining the Semantic Web , 2005 .

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

[22]  Wanxiang Che,et al.  Using word sense disambiguation for semantic role labeling , 2010, 2010 4th International Universal Communication Symposium.

[23]  Xiao-Feng Gu,et al.  Researches of Chinese sentence similarity based on HowNet , 2010, The 2010 International Conference on Apperceiving Computing and Intelligence Analysis Proceeding.

[24]  Tiejun Zhao,et al.  Chinese Named Entity Recognition with a Sequence Labeling Approach: Based on Characters, or Based on Words? , 2010, ICIC.

[25]  Oren Etzioni,et al.  The Tradeoffs Between Open and Traditional Relation Extraction , 2008, ACL.

[26]  Oren Etzioni,et al.  Open Information Extraction from the Web , 2007, CACM.

[27]  Yang Li-gong.  Entity Relation Extraction Method Using Semantic Pattern , 2007 .

[28]  Luis Gravano,et al.  Snowball: extracting relations from large plain-text collections , 2000, DL '00.

[29]  Qun Liu,et al.  HHMM-based Chinese Lexical Analyzer ICTCLAS , 2003, SIGHAN.

[30]  Martin Haspelmath,et al.  Word Classes and Parts of Speech , 2001 .

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

[32]  Zhang ZhixiongWu Zhenxin Xu Jian.  Review on Techniques of Entity Relation Extraction , 2008 .

[33]  Zhang Xian-fei.  Named entity relation extraction based on SVM training by positive and negative cases , 2008 .

[34]  Huang Rui-hong.  Chinese Automatic Entity Relation Extraction , 2007 .

[35]  Masao Fuketa,et al.  Extraction, selection and ranking of Field Association (FA) Terms from domain-specific corpora for building a comprehensive FA terms dictionary , 2010, Knowledge and Information Systems.

[36]  Doug Downey,et al.  Unsupervised named-entity extraction from the Web: An experimental study , 2005, Artif. Intell..

[37]  Lu Liu.  Named entity relation extraction based on SVM training by positive and negative cases: Named entity relation extraction based on SVM training by positive and negative cases , 2008 .