Implementation of Rule-Based Question Answering System

Abstract

Question Answering (QA) is a fastgrowing research area that brings together research from Information Retrieval, Information Extraction and Natural Language Processing. Question Answering system (QA), is a kind of new information retrieval system which can be queried with natural language and return knowledge directly. Natural language QA system includes analyzing question by using rules, resolving keywords and constructing query from keywords and then extracting answer from database. This paper presents question answering system by using rule-based method for medical domain. NL Questions are parsed with Stanford parser and keywords are extracted using predefined rules. Then SQL query statement is constructed using keywords and answers are extracted from medical database.The aim of the system is to generate short and specific answer to the question that is asked in the natural language in a specific domain. Evaluation will be based on the c@1 measure.