A statistical approach to machine translation
Computational Linguistics
The ATIS spoken language systems pilot corpus
HLT '90 Proceedings of the workshop on Speech and Natural Language
Learning language models through the ECGI method
Speech Communication - Eurospeech '91
Learning Subsequential Transducers for Pattern Recognition Interpretation Tasks
IEEE Transactions on Pattern Analysis and Machine Intelligence
Using domain information during the learning of a subsequential transducer
ICG! '96 Proceedings of the 3rd International Colloquium on Grammatical Inference: Learning Syntax from Sentences
Using knowledge to improve N-gram language modelling through the MGGI methodology
ICG! '96 Proceedings of the 3rd International Colloquium on Grammatical Inference: Learning Syntax from Sentences
Two Different Approaches for Cost-Efficient Viterbi Parsing with Error Correction
SSPR '96 Proceedings of the 6th International Workshop on Advances in Structural and Syntactical Pattern Recognition
Subsequential Functions: Characterizations, Minimization, Examples
Proceedings of the 6th International Meeting of Young Computer Scientists on Aspects and Prospects of Theoretical Computer Science
Finite-State Speech-to-Speech Translation
ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97) -Volume 1 - Volume 1
JANUS-III: Speech-to-Speech Translation in Multiple Languages
ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97) -Volume 1 - Volume 1
Finite-state transducers in language and speech processing
Computational Linguistics
| Hi-index | 0.00 |
Language Understanding in limited domains is here approached as a problem of language translation in which the target language is a formal language rather than a natural one. Finite-state transducers are used to model the translation process. Furthermore, these models are automatically learned from training data consisting of pairs of natural-language/formal-language sentences. The need for training data is dramatically reduced by performing a two-step learning process based on lexical/phrase categorization. Successful experiments are presented on a task consisting in the "understanding" of Spanish natural-language sentences describing dates and times, where the target formal language is the one used in the popular Unix command "at".