61. Baker C. L. (1989) English Syntax. MIT Press, Cambridge, Massachusetts.

62. Baker J. (1975) The Dragon system — an overview. IEEE Transactions on Acoustics, Speech, and SignalProcessing, 23, p. 24-29.

63. Baker J. (1979) Trainable grammars for speech recognition. In Speech Communication Papers for the 97thMeetingof the Acoustical Society of America, p. 547-550, Cambridge, Massachusetts. MIT Press.

64. Baldwin J. M. (1896) A new factor in evolution. American Naturalist, 30, p. 441-451. Продолжение нас. 536-553.

65. Ballard В. W. (1983) The *-minimax search procedure for trees containing chance nodes. ArtificialIntelligence, 21(3), p. 327-350.

66. Baluja S. (1997) Genetic algorithms and explicit search statistics. In Mozer M. C, Jordan M. I., andPetsche T. (Eds.), Advances in Neural Information Processing Systems, Vol. 9, p. 319-325. MIT Press, Cambridge, Massachusetts.

67. Bancilhon F., Maier D., Sagiv Y., and Ullman J. D. (1986) Magic sets and other strange ways toimplement logic programs. In Proceedings of the Fifth ACM Symposium on Principles of Database Systems, p. 1-16, New York. ACM Press.

68. Bar-Hillel Y. (1954) Indexical expressions. Mind, 63, p. 359-379.

69. Bar-Hillel Y. (1960) The present status of automatic translation of languages. In Alt F. L. (Ed.),Advances in Computers, Vol. 1, p. 91-163. Academic Press, New York.

70. Bar-Shalom Y. (Ed.) (1992) Multitarget-multisensor tracking: Advanced applications. Artech House,Norwood, Massachusetts.

71. Bar-Shalom Y. and FortmannT. E. (1988) Tracking and Data Association. Academic Press, New York.

72. Barrett A. and Weld D. S. (1994) Task-decomposition via plan parsing. In Proceedings of the TwelfthNational Conference on Artificial Intelligence (AAAI-94), p. 1117-1122, Seattle. AAAI Press.

73. Bartak R. (2001) Theory and practice of constraint propagation. In Proceedings of the Third Workshopon Constraint Programming for Decision and Control (CPDC-01), p. 7-14, Gliwice, Poland.

74. Barto A. G., Bradtke S. J., and Singh S. P. (1995) Learning to act using real-time dynamicprogramming. Artificial Intelligence, 73(\), p. 81-138.

75. Barto A. G., Sutton R. S., and Anderson С W. (1983) Neuronlike adaptive elements that can solve difficultlearning control problems. IEEE Transactions on Systems, Man and Cybernetics, 13, p. 834-846.

76. Barto A. G., Sutton R. S., and Brouwer P. S. (1981) Associative search network: A reinforcementlearning associative memory. Biological Cybernetics, 40(3), p. 201—211.

77. Barton G. E., Berwick R. C, and Ristad E. S. (1987) Computational Complexity and Natural Language.MIT Press, Cambridge, Massachusetts.

78. Barwise J. and Etchemendy J. (1993) The Language of First-Order Logic: Including the MacintoshProgram Tarski's World 4.0 (Third Revised and Expanded edition) Center for the Study of Language and Information (CSLI), Stanford, California.

79. Bateman J. A. (1997) Enabling technology for multilingual natural language generation: The KPMLdevelopment environment. Natural Language Engineering, 3(1), p. 15—55.

80. Bateman J. A., Kasper R. Т., Moore J. D., and Whitney R. A. (1989) A general organization ofknowledge for natural language processing: The penman upper model. Tech. rep., Information Sciences Institute, Marina del Rey, CA.