著者
Ajay N. Jain
タイトル
PARSEC: A Connectionist Learning Architecture for Parsing Spoken Language
日時
December 1991
概要
A great deal of research has been done developing parsers for natural language, but adequate solutions for some of the particular problems involved in spoken language are still in their infancy. Among the unsolved problems are: difficulty in constructing task-specific grammars, lack of tolerance to noisy input, and inability to effectively utilize complimentary non-symbolic information. This thesis describes PARSEC -- a system for generating connectionist parsing networks from example parses. PARSEC networks exhibit three strengths: * They automatically learn to parse, and they generalize well compared to hand-coded grammars. * They tolerate several types of noise without any explicit noise-modeling. * They can learn to use multi-modal input, e.g. a combination of intonation, syntax and semantics. The PARSEC network architecture relies on a variation of supervised back-propagation learning. The architecture differs from other connectionist approaches in that it is highly structured, both at the macroscopic level of modules, and at the microscopic level of connections. Structure is exploited to enhance system performance. Conference registration dialogs formed the primary development testbed for PARSEC. A separate simultaneous effort in speech recognition and translation for conference registration provided a useful data source for performance comparisons. Presented in this thesis are the PARSEC architecture, its training algorithms, and detailed performance analyses along several dimensions that concretely demonstrate PARSEC's advantages.
カテゴリ
CMUTR
Category: CMUTR
Institution: Department of Computer Science, Carnegie
        Mellon University
Abstract: A great deal of research has been done developing parsers
        for natural language, but adequate solutions for some of the
        particular problems involved in spoken language are still in
        their infancy.
        Among the unsolved problems are: difficulty in constructing
        task-specific grammars, lack of tolerance to noisy input, 
        and inability to effectively utilize complimentary non-symbolic
        information.
        
        This thesis describes PARSEC -- a system for generating 
        connectionist parsing networks from example parses.
        PARSEC networks exhibit three strengths:
        
        * They automatically learn to parse, and they generalize
        well compared to hand-coded grammars.
        
        * They tolerate several types of noise without any explicit 
        noise-modeling.
        
        * They can learn to use multi-modal input, e.g. a combination of
        intonation, syntax and semantics.
        
        The PARSEC network architecture relies on a variation of 
        supervised back-propagation learning.
        The architecture differs from other connectionist approaches in
        that it is highly structured, both at the macroscopic level of
        modules, and at the microscopic level of connections.
        Structure is exploited to enhance system performance.
        
        Conference registration dialogs formed the primary development
        testbed for PARSEC.
        A separate simultaneous effort in speech recognition and 
        translation for conference registration provided a useful data
        source for performance comparisons.
        
        Presented in this thesis are the PARSEC architecture, its 
        training algorithms, and detailed performance analyses along 
        several dimensions that concretely demonstrate PARSEC's 
        advantages.
        
        
Number: CMU-CS-91-208
Bibtype: TechReport
Month: dec
Author: Ajay N. Jain
Title: PARSEC: A Connectionist Learning Architecture for
        Parsing Spoken Language
Year: 1991
Address: Pittsburgh, PA
Super: @CMUTR