Improving Answer Extraction For Bangali Q/A System Using Anaphora-Cataphora Resolution

Human Computer Interaction (HCI) is a field of study to interact between humans (user) and computers on the design of computer technology. Question Answering (QA) system is one of the parts of HCI and a process of Information Retrieval (IR) in Natural Language Processing (NLP). In this research, it is attempted for a Bangla Question Answering System with simple sentences and experimented the system for both Bangla and English language. And it is tried to perform with semantic and syntactical analysis. Furthermore, for Bangla, a word net is constructed to demonstrate the system process. Our proposed method is a model in which it is easy for users to get most possible exact answer to their question easily and reduces the complexity of using noun instead of pronoun for the requested answer with respect to the given question queries for Bangla. It improves better answer extraction than naive approach.

[1]  Ralph Grishman,et al.  Information Extraction: Techniques and Challenges , 1997, SCIE.

[2]  Sanda M. Harabagiu,et al.  LASSO: A Tool for Surfing the Answer Net , 1999, TREC.

[3]  Stefan M. Rüger,et al.  A Simple Question Answering System , 2000, TREC.

[4]  Eduard H. Hovy,et al.  Question Answering in Webclopedia , 2000, TREC.

[5]  Jimmy J. Lin,et al.  Quantitative evaluation of passage retrieval algorithms for question answering , 2003, SIGIR.

[6]  Vasudeva Varma,et al.  A Naïve Approach for Monolingual Question Answering , 2009, CLEF.

[7]  Somnath Banerjee,et al.  Ensemble Approach for Fine-Grained Question Classification in Bengali , 2013 .

[8]  Somnath Banerjee,et al.  An Empirical Study of Combing Multiple Models in Bengali Question Classification , 2013, IJCNLP.

[9]  Asif Ekbal,et al.  Anaphora Resolution for Bengali: An Experiment with Domain Adaptation , 2013 .

[10]  Utpal Garain,et al.  GuiTAR-based Pronominal Anaphora Resolution in Bengali , 2013, ACL.

[11]  Ming-Wei Chang,et al.  Question Answering Using Enhanced Lexical Semantic Models , 2013, ACL.

[12]  Richard Socher,et al.  A Neural Network for Factoid Question Answering over Paragraphs , 2014, EMNLP.

[13]  Elsi Kaiser,et al.  Looking Back and Looking Forward: Anaphora and Cataphora in Italian , 2014 .

[14]  Sabir Ismail,et al.  Anaphora Resolution in Bangla Language , 2016 .

[15]  Dan Klein,et al.  Learning to Compose Neural Networks for Question Answering , 2016, NAACL.

[16]  M. M. Raghuwanshi,et al.  Question answering system on education acts using NLP techniques , 2016, 2016 World Conference on Futuristic Trends in Research and Innovation for Social Welfare (Startup Conclave).