Question Answering System (QA System)

Since there is an enormous number of internet documents, users must also examine the data to find relevant answers to their queries. We need Question Answering (QA) systems that are more reliable than current search engines, understanding sentence-level questions and analyzing the users’ intent.

QA system is expected in response to a submitted query, rather than a set of documents that may contain the answers. One common architecture for QA systems consists of question processing, document processing, and answer processing. The first represents the set of techniques implemented in QA systems that enable the interpretation of the questions and help identify its answer in the document collection. The second refers to the indexing model that enables the retrieval of paragraphs where the answer may lie. The third is the process of identifying in a paragraph the text snippet representing the answer to a given question.

QA research attempts to deal with a wide range of question types including fact, list, definition, how, why and cross-lingual questions. QA is considered as requiring more complex natural language processing (NLP) techniques than other types of information retrieval such as document retrieval, thus natural language search engines are sometimes regarded as the next step beyond current engines.

   ● www.wikipedia.org.

   ● Mitkov, R. ed. 2004. The Oxford Handbook of Computational Linguistics. Oxford University Press: Oxford.