232 search results - page 22 / 47 » Distortion Models for Statistical Machine Translation |
ACL
1998
15 years 24 days ago
1998
We describe a method for the fully automatic learning of hierarchical finite state translation models. The input to the method is transcribed speech utterances and their correspon...
105
click to vote
ACL
2012
13 years 1 months ago
2012
Bayesian approaches have been shown to reduce the amount of overfitting that occurs when running the EM algorithm, by placing prior probabilities on the model parameters. We appl...
ACL
2006
15 years 25 days ago
2006
This paper presents a novel training algorithm for a linearly-scored block sequence translation model. The key component is a new procedure to directly optimize the global scoring...
ACL
2007
15 years 27 days ago
2007
We present an approach to MT between Turkic languages and present results from an implementation of a MT system from Turkmen to Turkish. Our approach relies on ambiguous lexical a...
ACL
2008
15 years 27 days ago
2008
In statistical language modeling, one technique to reduce the problematic effects of data sparsity is to partition the vocabulary into equivalence classes. In this paper we invest...