268 search results - page 7 / 54 » Improving IBM Word Alignment Model 1 |
ACL
2007
15 years 1 months ago
2007
We present a general framework to incorporate prior knowledge such as heuristics or linguistic features in statistical generative word alignment models. Prior knowledge plays a ro...
95
Voted
ACL
2001
15 years 1 months ago
2001
We present a syntax-based statistical translation model. Our model transforms a source-language parse tree into a target-language string by applying stochastic operations at each ...
COLING
2010
14 years 6 months ago
2010
We present an unsupervised word segmentation model for machine translation. The model uses existing monolingual segmentation techniques and models the joint distribution over sour...
ACL
2006
15 years 1 months ago
2006
This paper compares different bilexical tree-based models for bilingual alignment. EM training for the new model benefits from the dynamic programming "hook trick". The ...
COLING
2010
14 years 6 months ago
2010
This paper1 presents an empirical approach to mining parallel corpora. Conventional approaches use a readily available collection of comparable, nonparallel corpora to extract par...