Multi-Alignment Templates Induction

Authors:
Algirdas Laukaitis;Olegas Vasilecas
Affiliations:
Faculty of Fundamental Sciences, Vilnius Gediminas Technical University, Saulėtekio al. 11, LT-10223 Vilnius, Lithuania, e-mail: algirdas.laukaitis@fm.vgtu.lt, olegas.vasilecas@fm.vgtu.lt;Faculty of Fundamental Sciences, Vilnius Gediminas Technical University, Saulėtekio al. 11, LT-10223 Vilnius, Lithuania, e-mail: algirdas.laukaitis@fm.vgtu.lt, olegas.vasilecas@fm.vgtu.lt
Venue:
Informatica
Year:
2008

Citing 14
Cited 0

A framework of a mechanical translation between Japanese and English by analogy principle

Proc. of the international NATO symposium on Artificial and human intelligence
A maximum entropy approach to natural language processing

Computational Linguistics
Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition

Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition
Review Article: Example-based Machine Translation

Machine Translation
The mathematics of statistical machine translation: parameter estimation

Computational Linguistics - Special issue on using large corpora: II
Decoding complexity in word-replacement translation models

Computational Linguistics
Fast decoding and optimal decoding for machine translation

ACL '01 Proceedings of the 39th Annual Meeting on Association for Computational Linguistics
Discriminative training and maximum entropy models for statistical machine translation

ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
BLEU: a method for automatic evaluation of machine translation

ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Feedback cleaning of machine translation rules using automatic evaluation

ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Cache-based Statistical Language Models of English and Highly Inflected Lithuanian

Informatica
Asymmetric Hybrid Machine Translation for Languages with Scarce Resources

CICLing '07 Proceedings of the 8th International Conference on Computational Linguistics and Intelligent Text Processing
Natural language based heavy personal assistant architecture for information retrieval and presentation

Proceedings of the 2007 conference on Human interface: Part II
Integrating all stages of information systems development by means of natural language processing

REFSQ'07 Proceedings of the 13th international working conference on Requirements engineering: foundation for software quality

Quantified Score

Hi-index	0.02

Visualization

Abstract

This paper examins approaches for translation between English and morphology-rich languages. Experiment with English-Russian and English-Lithuanian revels that “pure” statistical approaches on 10 million word corpus gives unsatisfactory translation. Then, several Web-available linguistic resources are suggested for translation. Syntax parsers, bilingual and semantic dictionaries, bilingual parallel corpus and monolingualWeb-based corpus are integrated in one comprehensive statistical model. Multi-abstraction language representation is used for statistical induction of syntactic and semantic transformation rules called multi-alignment templates. The decodingmodel is described using the feature functions, a log-linear modeling approach and A* search algorithm. An evaluation of this approach is performed on the English-Lithuanian language pair. Presented experimental results demonstrates that the multi-abstraction approach and hybridization of learning methods can improve quality of translation.