MBT2: a method for combining fragments of examples in example-based translation
Artificial Intelligence - Special issue: AI research in Japan
Machine translation divergences: a formal description and proposed solution
Computational Linguistics
A technique for computer detection and correction of spelling errors
Communications of the ACM
Three heads are better than one
ANLC '94 Proceedings of the fourth conference on Applied natural language processing
Pilot implementation of a Bilingual Knowledge Bank
COLING '90 Proceedings of the 13th conference on Computational linguistics - Volume 3
A method for distinguishing exceptional and general examples in example-based transfer systems
COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 1
A matching technique in Example-Based Machine Translation
COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 1
Learning translation templates from bilingual text
COLING '92 Proceedings of the 14th conference on Computational linguistics - Volume 2
Machine translation by case generalization
COLING '92 Proceedings of the 14th conference on Computational linguistics - Volume 2
Incremental translation utilizing constituent boundary patterns
COLING '96 Proceedings of the 16th conference on Computational linguistics - Volume 1
Study of practical effectiveness for machine translation using recursive chain-link-type learning
COLING '02 Proceedings of the 19th international conference on Computational linguistics - Volume 1
Panning for EBMT gold, or "Remembering not to forget"
Machine Translation
Hi-index | 0.00 |
This paper describes a self-modelling, incremental algorithm for learning translation rules from existing bilingual corpora. The notions of supracontext and subcontext are extended to encompass bilingual information through simultaneous analogy on both source and target sentences and juxtaposition of corresponding results. Analogical modelling is performed during the learning phase and translation patterns are projected in a multi-dimensional analogical network. The proposed framework was evaluated on a small training corpus providing promising results. Suggestions to improve system performance are this kind of analysis unquestionably leads to more computationally expensive and difficult to obtain systems. Our approach consists in a fully modular analogical framework, which can cope with lack of resources, and will perform even better when these are available.