Machine learning comprehension grammars for ten languages

Authors:
Patrick Suppes;Lin Liang;Michael Böttner
Affiliations:
Stanford University;Stanford University;-
Venue:
Computational Linguistics
Year:
1996

Citing 4
Cited 1

Naive physics, event perception, lexical semantics, and language acquisition

Naive physics, event perception, lexical semantics, and language acquisition
Lexical acquisition in the presence of noise and homonymy

AAAI '94 Proceedings of the twelfth national conference on Artificial intelligence (vol. 1)
Comprehension Grammars Generated from Machine Learning of Natural Languages

Machine Learning
Acquiring core meanings of words, represented as Jackendoff-style conceptual structures, from correlated streams of linguistic and non-linguistic input

ACL '90 Proceedings of the 28th annual meeting on Association for Computational Linguistics

Robotic machine learning of anaphora

Robotica

Quantified Score

Hi-index	0.00

Visualization

Abstract

Comprehension grammars for a sample of ten languages (English, Dutch, German, French, Spanish, Catalan, Russian, Chinese, Korean, and Japanese) were derived by machine learning from corpora of about 400 sentences. Key concepts in our learning theory are: probabilistic association of words and meanings, grammatical and semantical form generalization, grammar computations, congruence of meaning, and dynamical assignment of denotational value to a word.