User:KeenanFiedler/Question answering

Article body
Question answering (QA) is a computer science discipline within the fields of information retrieval and natural language processing (NLP) that is concerned with building systems that automatically answer questions that are posed by humans in a natural language.

Overview
A question-answering implementation, usually a computer program, may construct its answers by querying a structured database of knowledge or information, usually a knowledge base. More commonly, question-answering systems can pull answers from an unstructured collection of natural language documents.

Some examples of natural language document collections used for question answering systems include:


 * a locally stored collection of reference texts
 * internal organization documents and web pages—e.g., personnel files, patient records
 * compiled newswire reports
 * a set of Wikipedia pages
 * a subset of World Wide Web pages

Closed-domain question answering deals with questions under a specific domain (for example, medicine or automotive maintenance) and can exploit domain-specific knowledge frequently formalized in ontologies. Alternatively, "closed-domain" might refer to a situation where only a limited type of questions are accepted, such as questions asking for descriptive rather than procedural information. For instance, question answering systems have been constructed in the closed-domain of Alzheimer's disease, where machine reading applications have been given a corpus of literature on Alzheimer's disease and were then asked to answer questions about information in the texts.

History
Two early question answering systems were BASEBALL and LUNAR. BASEBALL could answer questions about data from one year of Major League Baseball.