A hybrid method for extracting relations between Arabic named entities

Relation extraction is a very useful task for several natural language processing applications, such as automatic summarization and question answering. In this paper, we present our hybrid approach to extracting relations between Arabic named entities. Given that Arabic is a rich morphological language, we build a linguistic and learning model to predict the positions of words that express a semantic relation within a clause. The main idea is to employ linguistic modules to ameliorate the results that are obtained from a machine learning-based method.Our method achieves encouraging performance. The empirical results indicate that the hybrid approach outperformed both the rule-based system (by 12%) and the machine learning-based approaches (by 9%) in terms of the F-score, to achieve 75.2% when applied to the same standard testing dataset, ANERCorp.

[1]  Christopher D. Manning,et al.  Better Arabic Parsing: Baselines, Evaluations, and Analysis , 2010, COLING.

[2]  Bruno Grilhères,et al.  Combinaison d'approches pour l'extraction automatique d'événements (Automatic events extraction by combining multiple approaches) [in French] , 2012, JEP-TALN-RECITAL.

[3]  Abdul Razak Hamdan,et al.  Human Talent Prediction in HRM using C4.5 Classification Algorithm , 2010 .

[4]  Slim Mesfar,et al.  Named Entity Recognition for Arabic Using Syntactic Grammars , 2007, NLDB.

[5]  Slim Mesfar.  Analyse morpho-syntaxique automatique et reconnaissance des entités nommées en arabe standard , 2008 .

[6]  Ollivier Haemmerlé,et al.  Approche générique pour l'extraction de relations à partir de textes , 2009, Actes d'IC.

[7]  Yassine Benajiba,et al.  Arabic Named Entity Recognition using Conditional Random Fields , 2008 .

[8]  John H. Holland.  Robust algorithms for adaptation set in a general formal framework , 1970 .

[9]  Yassine Benajiba,et al.  ANERsys: An Arabic Named Entity Recognition System Based on Maximum Entropy , 2009, CICLing.

[10]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[11]  Ralph Grishman,et al.  Discovering Relations among Named Entities from Large Corpora , 2004, ACL.

[12]  Abdelmajid Ben Hamadou,et al.  Multilingual Extraction of functional relations between Arabic Named Entities using NooJ platform , 2010 .

[13]  Zhu Qiaoming,et al.  Label propagation via bootstrapped support vectors for semantic relation extraction between named entities , 2009 .

[14]  Laetitia Vermeulen-Jourdan,et al.  ASGARD : un algorithme génétique pour les règles d'association. Application à la génomique , 2002, Rev. d'Intelligence Artif..

[15]  Jian Su,et al.  Discovering Relations Between Named Entities from a Large Raw Corpus Using Tree Similarity-Based Clustering , 2005, IJCNLP.

[16]  Hatem Haddad.  French Noun Phrase Indexing and Mining for an Information Retrieval System , 2003, SPIRE.

[17]  Abdelmajid Ben Hamadou,et al.  Recognition and Translation of Arabic Named Entities with NooJ Using a New Representation Model , 2011, FSMNLP.

[18]  Abdullah Alotayq.  Extracting Relations between Arabic Named Entities , 2013, TSD.

[19]  Yorick Wilks,et al.  Designing Adaptive Information Extraction for the Semantic Web in Amilcare , 2003 .

[20]  Kelvin K. W. Yau,et al.  Predicting electricity energy consumption: A comparison of regression analysis, decision tree and neural networks , 2007 .

[21]  Zhu Zhang,et al.  Weakly-supervised relation classification for information extraction , 2004, CIKM '04.

[22]  Abdelmajid Ben Hamadou,et al.  Enhancing Machine Learning Results for Semantic Relation Extraction , 2013, NLDB.

[23]  Tomasz Imielinski,et al.  Mining association rules between sets of items in large databases , 1993, SIGMOD Conference.

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

[25]  Lamia Hadrich Belguith,et al.  Clause-based Discourse Segmentation of Arabic Texts , 2012, LREC.

[26]  Pierre Zweigenbaum,et al.  A Hybrid Approach for the Extraction of Semantic Relations from MEDLINE Abstracts , 2011, CICLing.

[27]  Fabio Celli.  Searching for Semantic Relations between Named Entities in I-CAB. , 2009 .

[28]  Kareem Darwish,et al.  Simplified Feature Set for Arabic Named Entity Recognition , 2010, NEWS@ACL.

[29]  Rabiah Abdul Kadir,et al.  Overview of Biomedical Relations Extraction using Hybrid Rule-based Approaches , 2013 .

[30]  Abdelmajid Ben Hamadou,et al.  Recognition and translation Arabic-French of Named Entities: case of the Sport places , 2010, ArXiv.

[31]  Andrew McCallum,et al.  Modeling Relations and Their Mentions without Labeled Text , 2010, ECML/PKDD.

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

[33]  Guodong Zhou,et al.  Label propagation via bootstrapped support vectors for semantic relation extraction between named entities , 2009, Comput. Speech Lang..

[34]  Khaled Shaalan,et al.  A hybrid approach to Arabic named entity recognition , 2014, J. Inf. Sci..

[35]  Ossama Emam,et al.  Unsupervised Information Extraction Approach Using Graph Mutual Reinforcement , 2006, EMNLP.