Research Journal of Engineering and Technology

Megha Mishra ¹, Vishnu Kumar Mishra ², H. R. Sharma ³

Affiliations
1 SOA University, Bhubaneswar, IN
2 BIT, Durg, IN
3 R & D, RCET Raipur, IN

Abstract

Question classification is very important for question answering. This paper presents our research work on question classification through machine learning approach. In order to train the learning model, we designed a rich set of features that are predictive of question categories. We then performed a series of different experiments with the goal of determining the most discriminative set of features that yield the most accurate results.

Keywords

Question Answering, Machine Learning, Support Vector Machine, Question Classification, Lexical Features, Syntactical Features, Semantic Features, Combination of Features.

Full Text

     

Megha Mishra ¹, Vishnu Kumar Mishra ², H. R. Sharma ³

Affiliations
1 SOA University, Bhubneswar, IN
2 BIT, Durg, IN
3 R &D, RECT Raipur, IN

Abstract

Question classification is very important for question answering. This paper presents our research work on question classification through machine learning approaches. We have experimented with three machine learning algorithms: Nearest Neighbors (NN), Naïve Bayes (NB), and Support Vector Machines (SVM) using two kinds of features: bagof- words and bag-of n grams. The experiment results show that with only surface text features the SVM outperforms the other four methods for this task. Further, we propose to use a lexico-syntactic combined feature of question classification.

Keywords

Question Answering, Machine Learning, Support Vector Machine, Question Classifications, Lexical Features, Syntactical Feature.

Full Text