Cognitive Computing based Question-Answering System for Teaching Electrical Motor Concepts

Today is the era of ”Big Data”, and one has to spend ample amount of time to extract the meaningful information from such a huge store of data. It leads towards such a question answering system which can offer exact and precise answers to user queries. For that there is a requirement of understanding user queries effectively. Thus this paper proposes a cognitive computing powered question answering system in the field of education, which posses the power of Natural Language Processing (NLP). Here, cognitive computing provides the methods for synergism of several powers into a single architecture, NLP provides understanding of the user questions effectively, and Ontology endows with the techniques for the construction of robust knowledge base. So for the realistic implementation of the proposed architecture, the education domain has chosen and will be teaching electrical motor concepts to the edification of the students. General Terms Question-Answering System, NLP, Ontology.

[1]  Neil T. Heffernan,et al.  ElectronixTutor: an intelligent tutoring system with multiple learning resources for electronics , 2018, International Journal of STEM Education.

[2]  Alejandro Figueroa,et al.  Automatically generating effective search queries directly from community question-answering questions for finding related questions , 2017, Expert Syst. Appl..

[3]  Yiqiang Chen,et al.  ASELM: Adaptive semi-supervised ELM with application in question subjectivity identification , 2016, Neurocomputing.

[4]  Dietrich Klakow,et al.  Bridging the vocabulary gap between questions and answer sentences , 2015, Inf. Process. Manag..

[5]  Sean W. M. Siqueira,et al.  How to find people who can help to answer a question? - Analyses of metrics and machine learning in online communities , 2015, Comput. Hum. Behav..

[6]  Haiqin Yang,et al.  A deep learning approach for predicting the quality of online health expert question-answering services , 2016, J. Biomed. Informatics.

[7]  Zoe Falomir,et al.  comRAT-C: A computational compound Remote Associates Test solver based on language data and its comparison to human performance , 2015, Pattern Recognit. Lett..

[8]  Joachim Köhler,et al.  A knowledge graph based speech interface for question answering systems , 2017, Speech Commun..

[9]  Peng Peng,et al.  Answering top-K query combined keywords and structural queries on RDF graphs , 2017, Inf. Syst..

[10]  Sören Auer,et al.  SINA: Semantic interpretation of user queries for question answering on interlinked data , 2015, J. Web Semant..

[11]  Sadaoki Furui,et al.  Question answering using statistical language modelling , 2012, Comput. Speech Lang..

[12]  Anton Benz,et al.  Pragmatic question answering: A game-theoretic approach , 2016, Data Knowl. Eng..

[13]  Michele Lanza,et al.  Answering software evolution questions: An empirical evaluation , 2013, Inf. Softw. Technol..

[14]  Ming Li,et al.  Enhanced question understanding with dynamic memory networks for textual question answering , 2017, Expert Syst. Appl..

[15]  Devendra K. Chaturvedi,et al.  Ontology Based Knowledge Representation for Cognitive Decision Making in Teaching Electrical Motor Concepts , 2017, CSOC.

[16]  Devendra K. Chaturvedi,et al.  Semantic Network Based Cognitive, NLP Powered Question Answering System for Teaching Electrical Motor Concepts , 2018 .

[17]  Ulf Leser,et al.  Question answering for biology. , 2015, Methods.