A Novel Framework Using Zero Shot Learning Technique for a Non-Factoid Question Answering System

Akila Devi T. R., K. Javubar Sathick, A. Abdul Azeez Khan and L. Arun Raj
Additional contact information
Akila Devi T. R.: B. S. Abdur Rahman Crescent Institute of Science and Technology, Chennai, India
K. Javubar Sathick: B. S. Abdur Rahman Crescent Institute of Science and Technology, Chennai, India
A. Abdul Azeez Khan: B. S. Abdur Rahman Crescent Institute of Science and Technology, Chennai, India
L. Arun Raj: B. S. Abdur Rahman Crescent Institute of Science and Technology, Chennai, India

International Journal of Web-Based Learning and Teaching Technologies (IJWLTT), 2021, vol. 16, issue 6, 1-13

Abstract: Non-Factoid Question Answering (QA) is the next generation of textual QA systems, which gives passage level summaries for a natural language query, posted by the user. The main issue lies in the appropriateness of the generated summary. This paper proposes a framework for non-factoid QA system, which has three main components: (i) A deep neural network classifier, which produces sentence vector considering word correlation and context. (ii) Zero shot classifier that uses a multi-channel Convolutional Neural Network (CNN), to extract knowledge from multiple sources in the knowledge accumulator. This output acts as a knowledge enhancer that strengthens the passage level summary. (iii) Summary generator that uses Maximal Marginal Relevance (MMR) algorithm, which computes similarity among the query related answer and the sentences from zero shot classifier. This model is applied on the datasets WikiPassageQA and ANTIQUE. The experimental analysis shows that this model gives comparatively better results for WikiPassageQA dataset.

Date: 2021
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://services.igi-global.com/resolvedoi/resolve. ... IJWLTT.20211101.oa12 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:igg:jwltt0:v:16:y:2021:i:6:p:1-13

Access Statistics for this article

International Journal of Web-Based Learning and Teaching Technologies (IJWLTT) is currently edited by Mahesh S. Raisinghani

More articles in International Journal of Web-Based Learning and Teaching Technologies (IJWLTT) from IGI Global
Bibliographic data for series maintained by Journal Editor ().