natural language processing (NLP)

In COMPUTATIONAL LINGUISTICS, the computational processing of TEXTUAL materials in natural human languages. The aim is to devise techniques which will automatically analyze large quantities of spoken (transcribed) or written text in ways which are broadly parallel to what happens when humans carry out this task. The field emerged out of machine translation in the 1950s, and came to be much influenced by research in artificial intelligence. Later work concentrated on devising ‘intelligent programs’ (or ‘expert systems’) which would simulate aspects of human behavior, such as the way people use their knowledge of the world and their ability to draw inferences in order to make interpretations and reach conclusions. A more specifically linguistic contribution involves detailed SYNTACTIC, SEMANTIC and DISCOURSE analysis, often on a much larger scale than hitherto, and using the large amounts of lexical data currently available in computer CORPORA.