A statistical approach to machine translation
Computational Linguistics
MindNet: acquiring and structuring semantic information from text
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 2
Robust segmentation of Japanese text into a lattice for parsing
COLING '00 Proceedings of the 18th conference on Computational linguistics - Volume 1
Toward memory-based translation
COLING '90 Proceedings of the 13th conference on Computational linguistics - Volume 3
Using a broad-coverage parser for word-breaking in Japanese
COLING '00 Proceedings of the 18th conference on Computational linguistics - Volume 2
Acquisition of phrase-level bilingual correspondence using dependency structure
COLING '00 Proceedings of the 18th conference on Computational linguistics - Volume 2
Multilingual sentence generation
EWNLG '01 Proceedings of the 8th European workshop on Natural Language Generation - Volume 8
Overcoming the customization bottleneck using example-based MT
DMMT '01 Proceedings of the workshop on Data-driven methods in machine translation - Volume 14
DMMT '01 Proceedings of the workshop on Data-driven methods in machine translation - Volume 14
Towards a simple and accurate statistical approach to learning translation relationships among words
DMMT '01 Proceedings of the workshop on Data-driven methods in machine translation - Volume 14
Automatic Extraction of Super-Function From Bilingual Corpus
Electronic Notes in Theoretical Computer Science (ENTCS)
Incremental learning of transfer rules for customized machine translation
INAP'04/WLP'04 Proceedings of the 15th international conference on Applications of Declarative Programming and Knowledge Management, and 18th international conference on Workshop on Logic Programming
Hi-index | 0.00 |
This presentation describes an example-based English-Japanese machine translation system in which an abstract linguistic representation layer is used to extract and store bilingual translation knowledge, transfer patterns between languages, and generate output strings. Abstraction permits structural neutralizations that facilitate learning of translation examples across languages with radically different surface structure characteristics, and allows MT development to proceed within a largely language-independent NLP architecture. Comparative evaluation indicates that after training in a domain the English-Japanese system is statistically indistinguishable from a non-customized commercially available MT system in the same domain.