Implementing a language-independent MT methodology

Authors:
Sokratis Sofianopoulos;Marina Vassiliou;George Tambouratzis
Affiliations:
ILSP/Athena R.C., Athens, Greece;ILSP/Athena R.C., Athens, Greece;ILSP/Athena R.C., Athens, Greece
Venue:
MM '12 Proceedings of the First Workshop on Multilingual Modeling
Year:
2012

Citing 12
Cited 0

Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data

ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
BLEU: a method for automatic evaluation of machine translation

ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Hybrid data-driven models of machine translation

Machine Translation
Example-based machine translation: a review and commentary

Machine Translation
Automatic induction of bilingual resources from aligned parallel corpora: application to shallow-transfer machine translation

Machine Translation
METIS-II: low resource machine translation

Machine Translation
Inferring shallow-transfer machine translation rules from small parallel corpora

Journal of Artificial Intelligence Research
Statistical Machine Translation

Statistical Machine Translation
Multi-objective optimisation of real-valued parameters of a hybrid MT system using Genetic Algorithms

Pattern Recognition Letters
Cunei: open-source machine translation with relevance-based models of each translation instance

Machine Translation
Meteor 1.3: automatic metric for reliable optimization and evaluation of machine translation systems

WMT '11 Proceedings of the Sixth Workshop on Statistical Machine Translation
Word-Map Systems for Content-Based Document Classification

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews

Quantified Score

Hi-index	0.00

Visualization

Abstract

The current paper presents a language-independent methodology, which facilitates the creation of machine translation (MT) systems for various language pairs. This methodology is implemented in the PRESEMT hybrid MT system. PRESEMT has the lowest possible requirements on specialised resources and tools, given that for many languages (especially less widely used ones) only limited linguistic resources are available. In PRESEMT, the main translation process comprises two phases. The first one, Structure selection, determines the overall structure of a target language (TL) sentence, drawing on syntactic information from a small bilingual corpus. The second phase, Translation equivalent selection, relies on models extracted solely from monolingual corpora to implement translation disambiguation, determine intra-phrase word order and handle functional words. This paper proposes extracting information for disambiguation from the monolingual corpus. Experimental results indicate that such information substantially contributes in improving translation quality.