Skip to Content

Department of Linguistics

MU-Talk: Grammatical and Semantic Processing

Robert Mannell

Syntactic Processing

MU-Talk currently makes no attempt to parse incoming text. Whilst the grapheme-to-phoneme dictionary contains alternative possible parts-of-speech for each word, no attempt is currently made to determine the parts-of-speech for any word. Parsing into intonational phrases currently relies on punctuation.

Semantic Processing

MU-TALK currently has a primitive mechanism for determining semantic focus. Words are identified as function or content words with the help of an internal dictionary. A FIFO (first-in, first-out) buffer contains the last 30 content words. If a content word still exists in the buffer when that word occurs again, that new occurrence of the word is assumed to be "given" information and that word's ability to take a pitch accent is inhibited. Otherwise, the word is consider to be "new" information and it takes a pitch accent (and so helps to define an intonational phrase). This often results in too many accents, improper placement of accents and sometimes in the non-placement of a semantically appropriate pitch accent.