تسجيل الدخول

تسجيل

AUGMENTED TRANSITION NETWORK (ATN)

المؤلف:  John Field

المصدر:  Psycholinguistics

الجزء والصفحة:  P26

2025-07-30

850

AUGMENTED TRANSITION NETWORK (ATN)

A type of computer program designed by researchers in Artificial Intelligence, which attempts to represent the way in which an utterance is processed syntactically by a listener or reader. An ATN consists of a series of points at which accumulated evidence can lead to a ‘change of state’ and thus a new direction for the processing. The points occur after each complete phrase and sentence as well as after each word, thus enabling syntactic structures to be built.

 The processing occurs top-down. At the highest level, a network seeks evidence of a complete sentence in a pattern of a Noun Phrase followed by a Verb Phrase. Control then passes to the Noun Phrase level, where a parallel network seeks evidence of a determiner followed possibly by an Adjective and then followed by a Noun. Once the Noun has been located, the outcome is sent to the sentence level and a Verb Phrase is sought.

 While computer networks of this kind enable programs to process pieces of text, they are heavily dependent upon conventional sentence structures, and their top-down nature leads to many incorrect predictions and much backtracking.

See also: Artificial Intelligence, Syntactic parsing