A Novel Model for QUestion Answering Railway System: QUARS

Abstract

Objectives: The plethora of information available on the web makes it difficult to search for a specific and suitable query. So, Question Answering dialogue system becomes helpful to provide precise and short answers to users instead of lengthy documents or passages. Method: The main focus is on keyword based approach and partial linguistic analysis to process the query. The main component is Dialogue Manager which clarifies the conversation between user and system to resolve the elliptical and anaphoric problems. Findings/ Application: The paper is based upon the development of Question answering dialogue system in Hindi language for the domain of Railways. The study is restricted to Northern India alone. The existing system of Indian railway does not support Question Answering system while this novel system will provide anytime anywhere facility of enquiry about railway. The implemented system is quite simple, interactive and easy to use such that end user can ask the query using Hindi transliteration. The results are quite satisfactory as precision and recall values are 98% and 97% respectively. Keywords: Dialogue Manager, Partial Syntactic and Semantic Analysis, Query Processing, Question Answering Railway System