An Approach for Extracting Exact Answers to Question Answering (QA) System for English Sentences
Raju Barskar, Gulfishan Firdose Ahmed, Nepal Barskar · Procedia Engineering · 2012
Recent advances in Natural Language Processing (NLP) and AI are trying to build systems to the point where people may converse with a machine in natural language to get answers to their questions. The question answering system based on keywords search. This is similar to Web search. We are developing a Question Answering (QA) System for English sentences. The user should be able to access answer of their questions in a user friendly way, that is by questioning the system from the given English paragraph and the system will return the intended answer by searching in context of the paragraph using the repository of English dictionary. In this paper we present a Question/Answering system that takes advantage from category information by exploiting several models of question and answer categorization.A novel strategy, in addition to conventional search and NLP techniques, will of be used to construct the QA system. The focus is on context based retrieval of information. This paper provides a novel and efficient method for extracting exact textual answers from the returned documents that are retrieved by traditional IR system in large-scale collection of texts. For testing purpose, the proposed methodology is applied in text classification and the accompanying experimental results are compared with the output provided by a probabilistic based approach.