Automatic question-answer pairs generation and question similarity mechanism in question answering system

Aithal, Shivani G and Rao, Abhishek B and Singh, Sanjay (2021) Automatic question-answer pairs generation and question similarity mechanism in question answering system. Applied Intelligence, 51. ISSN 0924-669X

[img] PDF
13445.pdf - Published Version
Restricted to Registered users only

Download (547kB) | Request a copy


With the swift growth of the information over the past few years, taking full benefit is increasingly essential. QuestionAnswering System is one of the promising methods to access this much information. The Question Answering System lackshumans’ common sense and reasoning power and cannot identify unanswerable questions and irrelevant questions. Thesequestions are answered by making unreliable and incorrect guesses. In this paper, we address this limitation by proposing aQuestion Similarity mechanism. Before a question is posed to a Question-Answering system, it is compared with possiblegenerated questions of the given paragraph, and then a Question Similarity Score is generated. The Question Similaritymechanism effectively identifies the unanswerable and irrelevant questions. The proposed Question Similarity mechanismincorporates a human way of reasoning to identify unanswerable and irrelevant questions. This mechanism can avoid theunanswerable and irrelevant questions altogether from being posed to the Question Answering system. It helps the Question Answering Systems to focus only on the answerable questions to improve their performance. Along with this, we introduce an application of the Question Answering System that generates the question-answer pairs given a passage and is useful in several fields.

Item Type: Article
Uncontrolled Keywords: Question answering · Question generation · Question similarity · Universal sentence encoder · Question comprehension
Subjects: Engineering > MIT Manipal > Information and Communication Technology
Depositing User: MIT Library
Date Deposited: 23 Dec 2021 10:01
Last Modified: 23 Dec 2021 10:01

Actions (login required)

View Item View Item