Sciweavers

5 search results - page 1 / 1
» Multi-align: Combining Linguistic and Statistical Techniques...
Sort
View
AMTA
2004
Springer
13 years 10 months ago
Multi-align: Combining Linguistic and Statistical Techniques to Improve Alignments for Adaptable MT
Abstract. An adaptable statistical or hybrid MT system relies heavily on the quality of word-level alignments of real-world data. Statistical alignment approaches provide a reasona...
Necip Fazil Ayan, Bonnie J. Dorr, Nizar Habash
CIARP
2009
Springer
13 years 2 months ago
Incorporating Linguistic Information to Statistical Word-Level Alignment
Abstract. Parallel texts are enriched by alignment algorithms, thus establishing a relationship between the structures of the implied languages. Depending on the alignment level, t...
Eduardo Cendejas, Grettel Barceló, Alexande...
ACL
2011
12 years 8 months ago
Combining Morpheme-based Machine Translation with Post-processing Morpheme Prediction
This paper extends the training and tuning regime for phrase-based statistical machine translation to obtain fluent translations into morphologically complex languages (we build ...
Ann Clifton, Anoop Sarkar
ACL
2010
13 years 2 months ago
Boosting-Based System Combination for Machine Translation
In this paper, we present a simple and effective method to address the issue of how to generate diversified translation systems from a single Statistical Machine Translation (SMT)...
Tong Xiao, Jingbo Zhu, Muhua Zhu, Huizhen Wang
COLING
2010
12 years 11 months ago
Log-linear weight optimisation via Bayesian Adaptation in Statistical Machine Translation
We present an adaptation technique for statistical machine translation, which applies the well-known Bayesian learning paradigm for adapting the model parameters. Since state-of-t...
Germán Sanchis-Trilles, Francisco Casacuber...