Towards an Integration of Speech and Natural Language Processing
نویسنده
چکیده
Man-machine communication with natural language requires the integration of heterogeneous knowledges within a homogeneous framework. This problem concerns more particularly the speech/natural language interface. We propose in this paper an HPSG view of prosody illustrated with French intonation phenomena. We show that this linguistic theory is adapted for the integration representation: typed feature structures provide the homogenous knowledge representation framework and instantiation principles allow a precise representation of prosody/syntax relations. This paper presents a modiication of the phon feature structure of the signs together with some constraints and principles controling this prosody/syntax integration. Practically, we show that prosodic informations can help a parser in several ways: control (indications of units boundaries and indirectly on the government relations), dis-ambiguation (attachment heuristic) and pre-analysis (marks for particular contructions such as extraction, dislocation, etc.). We present in the last section a prosody-guided parser relying on this approach with some results.
منابع مشابه
Design and Implementation of an Intelligent Part of Speech Generator
The aim of this paper is to report on an attempt to design and implement an intelligent system capable of generating the correct part of speech for a given sentence while the sentence is totally new to the system and not stored in any database available to the system. It follows the same steps a normal individual does to provide the correct parts of speech using a natural language processor. It...
متن کاملA Comparison between Three Methods of Language Sampling: Freeplay, Narrative Speech and Conversation
Objectives: The spontaneous language sample analysis is an important part of the language assessment protocol. Language samples give us useful information about how children use language in the natural situations of daily life. The purpose of this study was to compare Conversation, Freeplay, and narrative speech in aspects of Mean Length of Utterance (MLU), Type-token ratio (TTR), and the numbe...
متن کاملTowards best practice in the development and evaluation of speech recognition components of a spoken language dialog system
Spoken Language Dialog Systems (SLDSs) aim to use natural spoken input for performing an information processing task such as call routing or train ticket reservation (Lamel et al., 1995). The main functionality of an SLDS are speech recognition, natural language understanding, dialog management, response generation and the speech synthesis. This article summarizes key aspects of the current pra...
متن کاملIntegrated speech and morphological processing in a connectionist continuous speech understanding for Korean
A new tightly coupled speech and natural language integration model is presented for a TDNN-based continuous possibly large vocabulary speech recognition system for Korean. Unlike popular n-best techniques developed for integrating mainly HMM-based speech recognition and natural language processing in a word level, which is obviously inadequate for morphologically complex agglutinative language...
متن کاملA Viterbi-based morphological analysis for speech and natural language integration
This paper presents a statistical/symbolic hybrid morphological analysis, called V-morph, for large scale speech and natural language integration for Korean. In the V-morph approach, statistical Viterbi-based lexical decoding and symbolic morphological modeling are integrated together on top of connectionist phoneme recognition engine. Linguistic characteristics of Korean are appropriately cons...
متن کامل