Question Answering

Question Answering

Ivan Habernal (University of West Bohemia, Czech Republic), Miloslav Konopík (University of West Bohemia, Czech Republic) and Ondrej Rohlík (University of West Bohemia, Czech Republic)
DOI: 10.4018/978-1-4666-0330-1.ch014
OnDemand PDF Download:
No Current Special Offers


Question Answering is an area of information retrieval with the added challenge of applying sophisticated techniques to identify the complex syntactic and semantic relationships present in text in order to provide a more sophisticated and satisfactory response to the user’s information needs. For this reason, the authors see question answering as the next step beyond standard information retrieval. In this chapter state of the art question answering is covered focusing on providing an overview of systems, techniques and approaches that are likely to be employed in the next generations of search engines. Special attention is paid to question answering using the World Wide Web as the data source and to question answering exploiting the possibilities of Semantic Web. Considerations about the current issues and prospects for promising future research are also provided.
Chapter Preview

Overview And Background

Question answering (QA) addresses the problem of finding answers to questions posed in natural language.

Traditionally the QA system is expected to provide one concise answer to the user's query. For the question “When did Thomas Jefferson die?” the ideal answer might be “July 4, 1826” with “Thomas Jefferson died on the Fourth of July, 1826” being another possibility. The exact way an answer is presented depends on the context and the application.

More formally, question answering is the task which when given a query in natural language, aims at finding one or more concise answers in the form of sentences or phrases. Due to its high requirements in terms of precision and conciseness, question answering is often seen as a sub-discipline of information retrieval (IR). Compared to IR, QA poses the added challenge of applying techniques developed in the field of natural language processing (NLP), such as the identification of the complex syntactic and semantic relationships present in the text.

QA systems even move a step further in natural language understanding with respect to standard IR systems (which have typical representatives in Web search engines) because they generally do not respond to a question but to a query in a form of a set of words where syntactic structure is ignored. Moreover, Web search engines do not return an answer, but rather a set of documents which are considered relevant to the query, i.e., which it is hoped will be useful to the user. Still, IR technology remains a fundamental building block of QA, in particular for those QA systems that use Web as their data collection (Quarteroni, 2007).

Complete Chapter List

Search this Book: