On adaptive acquisition of language

A system that automatically acquires a language model for a particular task from semantic-level information is described. This is in contrast to systems with predefined vocabulary and syntax. The purpose of the system is to map spoken or typed input into a machine action. To accomplish this task a medium-grain neural network is used. An adaptive training procedure is introduced for estimating the connection weights. It has the advantages of rapid, single-pass and order-invariant learning. The resulting weights have information-theoretic significance and do not require gradient search techniques for their estimation. The system was experimentally evaluated on three text-based tasks; a three-class inward-call manager with an acquired vocabulary of over 1600 words, a 15-action subset of the DARPA Resource Manager with an acquired vocabulary of over 700 words, and discrimination between idiomatic phrases meaning yes or no.<<ETX>>

[1]  George W. Furnas,et al.  Experience with an adaptive indexing scheme , 1985, CHI '85.

[2]  Alexander H. Waibel,et al.  Incremental Parsing by Modular Recurrent Connectionist Networks , 1989, NIPS.

[3]  D. W. Tufts,et al.  Statistical Communication Theory , 1958 .

[4]  E. Mark Gold,et al.  Language Identification in the Limit , 1967, Inf. Control..

[5]  Marvin Minsky,et al.  Perceptrons: An Introduction to Computational Geometry , 1969 .

[6]  Kenneth Ward Church,et al.  Word Association Norms, Mutual Information, and Lexicography , 1989, ACL.

[7]  S. T. Dumais,et al.  Human factors and behavioral science: Statistical semantics: Analysis of the potential performance of key-word information systems , 1983, The Bell System Technical Journal.

[8]  Stephen E. Levinson,et al.  Speaker independent phonetic transcription of fluent speech for large vocabulary speech recognition , 1989, International Conference on Acoustics, Speech, and Signal Processing,.

[9]  B. Widrow,et al.  Stationary and nonstationary learning characteristics of the LMS adaptive filter , 1976, Proceedings of the IEEE.

[10]  S.E. Levinson,et al.  Structural methods in automatic speech recognition , 1985, Proceedings of the IEEE.

[11]  Eve V. Clark,et al.  The principle of contrast: A constraint on language acquisition. , 1987 .

[12]  Van Rijsbergen,et al.  A theoretical basis for the use of co-occurence data in information retrieval , 1977 .

[13]  Leslie G. Valiant,et al.  A theory of the learnable , 1984, STOC '84.

[14]  Kumpati S. Narendra,et al.  Learning Automata - A Survey , 1974, IEEE Trans. Syst. Man Cybern..

[15]  Mitchell P. Marcus,et al.  Parsing a Natural Language Using Mutual Information Statistics , 1990, AAAI.

[16]  Patti Price,et al.  The DARPA 1000-word resource management database for continuous speech recognition , 1988, ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing.

[17]  James L. McClelland,et al.  Mechanisms of Sentence Processing: Assigning Roles to Constituents of Sentences , 1986 .

[18]  Jeffrey Mark Siskind,et al.  Acquiring Core Meanings of Words, Represented as Jackendoff-Style Conceptual Structures, from Correlated Streams of Linguistic and Non-Linguistic Input , 1990, ACL.

[19]  J J Hopfield,et al.  Neural computation by concentrating information in time. , 1987, Proceedings of the National Academy of Sciences of the United States of America.

[20]  Rodney A. Brooks,et al.  A Robust Layered Control Syste For A Mobile Robot , 2022 .

[21]  John R. Pierce,et al.  Symbols, signals, and noise , 1961 .

[22]  Padhraic Smyth,et al.  The Induction of Probabilistic Rule Sets - The Itrule Algorithm , 1989, ML.

[23]  Stephen E. Levinson,et al.  A conversational-mode airline information and reservation system using speech input and output , 1980 .

[24]  Stephen E. Levinson,et al.  Continuously variable duration hidden Markov models for automatic speech recognition , 1986 .

[25]  Biing-Hwang Juang,et al.  The segmental K-means algorithm for estimating parameters of hidden Markov models , 1990, IEEE Trans. Acoust. Speech Signal Process..

[26]  Stephen E. Levinson,et al.  A new task‐oriented conversational mode speech recognition system , 1983 .

[27]  Padhraic Smyth,et al.  An Information Theoretic Approach to Rule-Based Connectionist Expert Systems , 1988, NIPS.

[28]  Padhraic Smyth,et al.  A Rule-Based Approach to Neural Network Classifiers , 1990 .

[29]  Chin-Hui Lee,et al.  Automatic recognition of keywords in unconstrained speech using hidden Markov models , 1990, IEEE Trans. Acoust. Speech Signal Process..

[30]  Gerald Salton,et al.  Automatic text processing , 1988 .

[31]  Leslie G. Valiant,et al.  Computational limitations on learning from examples , 1988, JACM.

[32]  Eric Wanner,et al.  Language acquisition: the state of the art , 1982 .

[33]  Victor Zue,et al.  Recent Progress on the VOYAGER System , 1990, HLT.

[34]  M. M. Sondhi,et al.  An adaptive echo canceller , 1967 .