Natural Language Processing based New Approach to Design Factoid Question Answering System

Citations Over TimeTop 24% of 2020 papers

Abstract

The field of text mining which deals with the providing of answers to the questions of the users is also one of the hot topics for researchers. The difficulty seen in the proper answering of the questions needs to be resolved. The large variety of questions fails in the QA system. In this paper, Natural Language Processing (NLP) has been used which deals with the processing of the data that comes in any form like text, video, image, or audio. This NLP comes under the field of artificial intelligence (AI), which is used in the field of question answering (QA) system. Here proposed work for designing a system that works for factoid QA which will answer the questions that are asked by the users. Lexical Chain and Keyword analysis are used in our system for the answering of questions from a given set of articles. The reasoning system is used for the validity of the answering. The experiment here is done with the SQUAD dataset. In our experiment, the accuracy obtained for the passage retrieval using TFIDF is 69.69%. The overall average of the correct prediction of the answer is 69.93%.

Related Papers

• → Improving the Question Answering Quality using Answer Candidate Filtering based on Natural-Language Features(2021)4 cited
• Question answering systems: a partial answer(2007)
• → Similarity Detection of Natural-Language Questions and Answers using the VANiLLa dataset(2021)2 cited
• → Mobile System Using Natural Language Annotations for Question Answering(2009)1 cited
• → Analysis on the Language Independent and Dependent Aspects of Deep Learning based Question Answering Systems(2020)