INTRODUCTION Question Answer system is a man machine communication device. Thebasic idea of QA system is to provide correct responses to the questionsin a human like manner giving short and accurate answers.With the advent of Internet and the World Wide Web (WWW) massiveamount of textual information are available to general public. However, itis difficult to find specific information with them.Question answering system has deduction capability with the help ofwhich users can retrieve the exact answer to a question instead of a set ofdocuments.QA systems typically require a great deal of human effort, in order tocreate linguistic rules that can cope with the vast variety of questions thatcan be asked, and the many different ways in which they can beformulated.
OUR PROJECT Our project on question answering system deals with three differentstages:1. The naïve bayesian classifier stage which classifies answers in terms of a simple yes/no as per the question asked.2. Exact answer extraction stage which gives the exact answer of a given question asked by the user For eg: Who is the president of America? Answer: Barack Obama3. The Passage Retrieval stage which gives the the relevant passage from the database from where the answer to a given question might be found. Our QA system facilitates the user to ask a question in any form as user wishes and provides them with the exact answer or passage containing the answer.
TECNIQUES (contd..)QUESTION CLASSIFICATION: The task of the Question Classification module is to assign a semantic category to a given question. Every question can be classified into following taxonomy
TECNIQUES (contd..)PASSAGE RETRIEVAL: The goal of the passage retrieval module is to find relevant documents from a given collection. A document is deemed as relevant if it can potentially contain the correct answer for a given question.ANSWER EXTRACTION: The answer extraction module is the last module in the QA pipeline and, therefore, its goal is to extract an answer from the relevant passages returned by the passage retrieval module, and present the answer.
APPLICATION (Zhang & Lee, 2003) used a naive Bayesian classifier for task ofquestion classification, trained on the standard data set for questionclassification of Li & Roth. Question Answering System can be applied to prove other algorithmslike Support Vector Machine (SVM) and K Nearest Neighbor (KNN)algorithm. Exact answer to a given question can be extracted using surface textpatterns that give the different forms in which answer can appear.(Ravichandran & Hovy, 2001) developed a method to learn patterns,using bootstrapping. The technique works in two-phases, where the first (Algorithm 1) isused to acquire patterns from a set of seed examples, and the secondvalidates the learnt patterns by calculating their precision.
FUTURE ENHANCEMENTThe Question Answering System (QA) can be used to apply SupportVector Machine (SVM) and K Nearest Neighbor (KNN) algorithms.The system can be further extended to the field of Machine Learning.Machine Learning is the field of study that is concerned with the questionof how to construct computer programs that automatically improve withexperience (Mitchell, 1997). Within this view, a computer programis said to learn from an experience with respect to some task, if theprogram’s performance at the task improves with the experience. The field of machine learning is divided into three broad categories :1. Supervised learning2. Unsupervised learning3. Reinforced learningThese can be stepwise implemented by enhancing the current system.
LITERATURE SURVEY AnswerBus Question Answering System Zhiping Zheng, School ofInformation University of Michigan. Steven Abney, Michael Collins, and Amit Singhal. AnswerExtraction. Proceedings of ANLP 2000. Seattle, WA. April 29 - May 3,2000. From search engines to question answering system-The problemsof World Knowledge, Relevance,Precision andDeduction, Lotfi.A.Zadeh, University of California. Peter Clark, John Thompson, and Bruce Porter. A knowledge-based approach to question answering. AAAI’99 Fall Symposium onQuestion-Answering Systems. Orlando, Florida. 1999.
CONCLUSION Existing search engines, with Google at the top, have many trulyremarkable capabilities. But there is a basic limitation – search engines donot have deduction capability – a capability which a question-answeringsystem is expected to have. Nevertheless, search engines are extremelyuseful because a skilled human user can get around search enginelimitations. In this perspective, a search engine may be viewed as a semi-mechanized question-answering system. Our project on Question Answering system aims at providing exactanswers to user’s question irrespective of the form in which the question isasked. Apart from this another stage of the project also provides the userwith the entire passage containing data related to user’s question whereinthe correct answer can be extracted. We have also succesfully applied the Naïve Bayesian approach ofretrieving answers to a particular question.