A FULLY AUTOMATIC QUESTION ANSWERING SYSTEM TO IMPROVE E-LEARNING

Abstract

Automatic Question Answering is a type of information retrieval. Given a collection of documents (such as the World Wide Web or a local collection) the system should be able to retrieve answers to questions posed in natural language. Automatic Question Answering is regarded as requiring more complex natural language processing (NLP) techniques than other types of information retrieval such as document retrieval, and it is regarded as the next step beyond search engines. Looking at increasing trend in distance education and availability of online E-Learning material; students need a question answering system to effectively utilize the material and to improve E-Learning. This report presents an automatic Question Answering System (QAS) for E-Leaming domain. The accuracy of answers has been increased by incorporating various NLP tools and a novel Word Sense Disambiguation (WSD) algorithm. The approach used is to utilize domain knowledge as much as possible to improve the performance of the system. The system utilizes template based approach to extract quality answers from passages. The WSD algorithm is designed specifically for closed domain question answering systems by utilizing the WordNet (English dictionary) and domain corpus (domain dataset). The WSD algorithm is applied in query expansion phase of the question answering system to expand query terms for relevant senses only. The question answering system and WSD algorithm have been implemented in C/C++ on Linux platform using various tools such as Wordnet 3.1, automatic question classifier, NE recognizer, SEFT (retrieval engine) and Beagle desktop search tool.