Abstract
In this paper a hybrid algorithm for Punjabi Question Answering system has been implemented. A hybrid system that works on various kinds of question types using the concepts of pattern matching as well as mathematical expression for developing a scoring system that can help differentiate best answer among available set of multiple answers found by the algorithm and is also domain specific like sports. The proposed system is designed and built in such a way that it increases the accuracy of question answering system in terms of recall and precision and is working for factoid questions and answers text in Punjabi. The system constructs a novel mathematical scoring system to identify most accurate probable answer out of the multiple answer patterns.The answers are extracted for various types of Punjabi questions. The experimental results are evaluated on the basis of Precision, Recall, F-score and Mean Reciprocal Rank (MRR). The average value of precision, recall, f-score and Mean Reciprocal Rank is 85.66%, 65.28%, 74.06%, 0.43 (normalised value) respectively. MRR values are Optimal. These values are act as discrimination factor values between one relevant answer to the other relevant answer.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Gupta, V., Lehal, G.S.: A Survey of Text Mining Techniques and Applications. J. Emerging Technologies in Web Excellence 1 (2009)
Hirschman, L., Gaizauskas, R.: Natural language question answering: The view from here. Natural Language Engineering 7(4), 275–300
Sahu, S., Vasnik, N., Roy, D.: Proshanttor: A Hindi Question Answering System. J. Computer Science & Information Technology (IJCSIT) 4, 149–158 (2012)
Ramprasath, M., Hariharan, S.: A Survey on Question Answering System. J. International Journal of Research and Reviews in Information Sciences (IJRRIS) 2, 171–178 (2012)
Kolomiyets, O., Moens, M.-F.: A survey on question answering technology from an information retrieval perspective. J. Info Sciences 181, 5412–5434 (2011)
Frank, A., Krieger, H.-U., Xu, F., Uszkoreit, H., Crysmann, B., Jörg, B., Schäfer, U.: Question Answering from structured knowledge sources. J. of Applied Logic 5, 20–48 (2006)
Zhenqiu, L.: Design of Automatic Question Answering base on CBR. J. Procedia Engineering 29, 981–985 (2011)
Tallez-Valero, A., Montes-y-Gomez, M., Villasenor-Pineda, L., Padilla, A.P.: Learning to select the correct answer in multi-stream question answering. J. Information Processing and Management 47, 856–869 (2011)
Ko, J., Si, L., Nyberg, E.: Combining evidence with a probabilistic framework for answer ranking and answer merging in question answering. J. Information Processing and Management 46, 541–554 (2010)
Ahn, C.-M., Lee, J.-H., Choi, B., Park, S.: Question Answering System with Recommendation using Fuzzy Relational Product Operator. In: iiWAS 2010 Proceedings, pp. 853–856. ACM (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Gupta, P., Gupta, V. (2014). Hybrid Approach for Punjabi Question Answering System. In: Thampi, S., Gelbukh, A., Mukhopadhyay, J. (eds) Advances in Signal Processing and Intelligent Recognition Systems. Advances in Intelligent Systems and Computing, vol 264. Springer, Cham. https://doi.org/10.1007/978-3-319-04960-1_12
Download citation
DOI: https://doi.org/10.1007/978-3-319-04960-1_12
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-04959-5
Online ISBN: 978-3-319-04960-1
eBook Packages: EngineeringEngineering (R0)