English-Japanese example-based machine translation using abstract linguistic representations

Authors:
Chris Brockett;Takako Aikawa;Anthony Aue;Arul Menezes;Chris Quirk;Hisami Suzuki
Affiliations:
Microsoft Research, Redmond, WA;Microsoft Research, Redmond, WA;Microsoft Research, Redmond, WA;Microsoft Research, Redmond, WA;Microsoft Research, Redmond, WA;Microsoft Research, Redmond, WA
Venue:
COLING-MTIA '02 Proceedings of the 2002 COLING workshop on Machine translation in Asia - Volume 16
Year:
2002

Citing 10
Cited 2

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
A best-first alignment algorithm for automatic extraction of transfer mappings from bilingual corpora

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

Quantified Score

Hi-index	0.00

Visualization

Abstract

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.