Abstrait

Question Analysis and Classification for Question Answering System

Madhu Siddhartha1, Ashish Kumar Singh2*, Sanjay K Dwivedi3

Question answering(Q/A) are part of information retrieval (IR) research in which users instead of providing a few keywords to retrieve a set of documents, actually provide complete questions and expect from the QA system to get the most relevant answers(s). This way an efficient Q/A system will be more helpful in providing an accurate answer to a question instead of a query based information retrieval system. No one could have predicted that question answering system would become an indispensable technology for Information Retrieval that would enable the creation of new technologies for information retrieval. The Q/A systems have now been recognized as one of the challenging problem in IR. The task of question classification is one of the most important steps for the efficiency and relevancy of any QA system design. After going through the available literature on the QA systems, we found that there could be different classification of questions. This paper first discusses the general architecture of a QA system and then proposes a more elaborative classification of questions along with some major approaches used for classification in order to design a suitable question answering (QA) system.