A Advanced Approach To Construct E-Learning QA System
DOI:
https://doi.org/10.26438/ijcse/v6i8.8083Keywords:
Answer Selection, Question-Answer pairs, Pair wise learning technique, Community-based Question AnsweringAbstract
The Novel approach can yield high levels of performance and nicely complements traditional question answering techniques driven by information extraction. In order for question answering systems to benet from this vast store of useful knowledge, they must copy with large volumes of useless data. Question Answering systems (QA) uses similarity in questions and ranking the relevant answer to user. The web gives large data and that require more time as well as no relevancy in answers. To solve this problem proposed system proposed novel Pair wise Learning to rANk model i.e PLANE which can quantitatively rank answer candidates from the relevant question pool. Specially, it uses two components i.e online learning component and one online search component. Our model is effective as well as achieves better performance than several existing questions answer selection system. User gets recommendation based on his profile. User recommend the new question to his friend and this is trust analysis so user can get top recommendation of newly arrived question of languages.
References
[1] W. Wei, Z. Ming, L. Nie, G. Li, J. Li, F. Zhu, T. Shang, and C. Luo, Exploring heterogeneous features for query-focused summarization of categorized community answers, Inf. Sci., vol. 330, pp. 403423, 2016.
[2] X. Li, Y. Ye, and M. K. Ng, Multivcrank with applications to image retrieval, TIP, vol. 25, no. 3, pp. 13961409, 2016.
[3] W. Wei, G. Cong, C. Miao, F. Zhu, and G. Li, Learning to find topic experts in twitter via different relations, TKDE, vol. 28, no. 7, pp. 17641778, 2016
[4] W. Wei, B. Gao, T. Liu, T. Wang, G. Li, and H. Li, A ranking approach on large-scale graph with multidimensional heterogeneous information, TOC, vol. 46, no. 4, pp. 930944, 2016.
[5] X. Wei, H. Huang, C. Lin, X. Xin, X. Mao, and S. Wang, Reranking voting-based answers by discarding user behavior biases, in Proceedings of IJCAI15, 2015, pp. 23802386.
[6] Q. H. Tran, V. Duc, Tran, T. T. Vu, M. L. Nguyen, and S. B. Pham, Jaist: Combining multiple features for answer selection in community question answering, in Proceedings of SemEval15. ACL, 2015, pp. 215C219.
[7] Savenkov, Ranking answers and web passages for non-factoid question answering: Emory university at TREC liveqa, in Proceedings of TREC15, 2015.
[8] A Joint Segmentation and Classification Framework for Sentence Level Sentiment Classification Duyu Tang, Bing Qin, Furu Wei, Li Dong, Ting Liu, and Ming Zhou. EEE/ACM transjectiom
on audio search data, language processing, no. 11,november 015
[9] Q. Le and T. Mikolov, Distributed representations of sentences and documents, in Proceedings of ICML14. Morgan Kaufmann Publishers Inc., 2014, pp. 11881196.
[10] T. Joachims, L. Granka, B. Pan, H. Hembrooke, and G. Gay, Accurately interpreting clickthrough data as implicit feedback, in Proceedings of SIGIR05. ACM, 2005, pp. 154161.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors contributing to this journal agree to publish their articles under the Creative Commons Attribution 4.0 International License, allowing third parties to share their work (copy, distribute, transmit) and to adapt it, under the condition that the authors are given credit and that in the event of reuse or distribution, the terms of this license are made clear.
