Prosodic Aids to Syntactic and Semantic Analysis of Spoken English

Prosodic Aids to Syntactic and Semantic Analysis of Spoken English Chris Rowles and Xiuming Huang AI Systems Section Australia and Overseas Telecommunications Corporation Telecommunications Research Laboratories PO Box 249, Clayton, Victoria, 3168, Australia Internet: c.rowles@td.oz.au ABSTRACT Prosody can be useful in resolving certain lex- ical and structural ambiguities in spoken English. In this paper we present some results of employ- ing two types of prosodic information, namely pitch and pause, to assist syntactic and semantic analysis during parsing. 1. INTRODUCTION In attempting to merge speech recognition and natural language understanding to produce a system capable of understanding spoken dia- logues, we are confronted with a range of prob- lems not found in text processing. Spoken language conversations are typically more terse, less grammatically correct, less well- structured and more ambiguous than text (Brown & Yule 1983). Additionally, speech recognition systems that attempt to extract words from speech typically produce word insertion, deletion or substitution errors due to incorrect recognition and segmentation. The motivation for our work is to combine speech recognition and natural language under- standing (NLU) techniques to produce a system which can, in some sense, understand the intent of a speaker in telephone-based, information seeking dialogues. As a result, we are interested in NLU to improve the semantic recognition accu- racy of such a system, but since we do not have explicit utterance segmentation and structural in- formation, such as punctuation in text, we have explored the use of prosody. Intonation can be useful in understanding dia- logue structure (c.f. Hirschberg & Pierrehumbert 1986), but parsing can also be assisted. (Briscoe & Boguraev 1984) suggests that if prosodic struc- ture could be derived for the noun compound Bo- ron epoxy rocket motor chambers, then their parser LEXICAT could reduce the fourteen licit 112 morphosyntactic interpretations to one correct analysis without error (p. 262). (Steedman 1990) explores taking advantage of intonational struc- ture in spoken sentence understanding in the combinatory categorial grammar formalism. (Bear & Price 1990) discusses integrating proso- dy and syntax in parsing spoken English, relative duration of phonetic segments being the one as- pect of prosody examined. Compared with the efforts expended on syn- tactic/semantic disambiguation mechanisms, prosody is still an under-exploited area. No work has yet been carded out which treats prosody at the same level as syntax, semantics, and prag- matics, even though evidence shows that proso- dy is as important as the other means in human understanding of utterances (see, for example, experiments reported in (Price et a11989)). (Scott & Cutler 1984) noticed that listeners can suc- cessfully identify the intended meaning of ambig- uous sentences even in the absence of a disambiguating context, and suggested that speakers can exploit acoustic features to high- light the distinction that is to be conveyed to the listener (p. 450). Our current work incorporates certain prosod- ic information into the process of parsing, com- bining syntax, semantics, pragmatics and prosody for disambiguation 1 . The context of the work is an electronic directory assistance system (Rowles …

Content truncated to 500 words