Natural-language processing system using a large corpus

作者: Robert J. Freeman

DOI:

关键词: MathematicsSource materialGrammaticalityNatural language processingParsingEquivalence (formal languages)Artificial intelligence

摘要: A computer-parsing system using vectors (lists) to represent natural-language elements, providing a robust, distributed way score grammaticality of an input string by as source material large corpus text. The uses recombining asymmetric associations syntactically similar strings form the vectors. equivalence lists for subparts build longer in order controlled potential parse be scored. power recombination vector elements building provides means representing collocational complexity. Grammaticality scoring is based upon number and similarity elements.

参考文章(20)
Jonathan P. Yamron, James K. Baker, Janet M. Baker, Laurence S. Gillick, Systems and methods for word recognition ,(1996)
Elizabeth D. Liddy, Mary E. McKenna, Woojin Paik, Ming Li, Natural language information retrieval system and method ,(1996)
Andrew Scott Kehler, Adam L. Berger, Robert Leroy Mercer, Peter Fitzhugh Brown, Pietra Vincent Joseph Della, Pietra Stephen Andrew Della, Language translation apparatus and method using context-based translation models ,(1994)
Ido Dagan, Lillian Lee, Fernando C. N. Pereira, Similarity-Based Models of Word Cooccurrence Probabilities Machine Learning. ,vol. 34, pp. 43- 69 ,(1999) , 10.1023/A:1007537716579
Dekang Lin, An Information-Theoretic Definition of Similarity international conference on machine learning. pp. 296- 304 ,(1998)
Elizabeth D. Liddy, Edmund S. Yu, Woojin Paik, Ming Li, Multilingual document retrieval system and method using semantic vector matching ,(1996)
Elizabeth D. Liddy, Bhaskaran Balakrishnan, Mary E. McKenna, Edmund S. Yu, Woojin Paik, David L. Snyder, Michael L. Weiner, Theodore G. Diamond, User interface and other enhancements for natural language information retrieval system and method ,(1996)