18 search results - page 2 / 4 » Regenerating Hypotheses for Statistical Machine Translation |
73
Voted
NAACL
2007
14 years 11 months ago
2007
This paper describes an efficient method to extract large n-best lists from a word graph produced by a statistical machine translation system. The extraction is based on the k sh...
93
Voted
EMNLP
2008
14 years 11 months ago
2008
Minimum Error Rate Training (MERT) is an effective means to estimate the feature function weights of a linear model such that an automated evaluation criterion for measuring syste...
80
Voted
ACL
2003
14 years 11 months ago
2003
In statistical machine translation, the generation of a translation hypothesis is computationally expensive. If arbitrary wordreorderings are permitted, the search problem is NP-h...
75
Voted
EMNLP
2008
14 years 11 months ago
2008
We present Minimum Bayes-Risk (MBR) decoding over translation lattices that compactly encode a huge number of translation hypotheses. We describe conditions on the loss function t...
ACL
1998
14 years 11 months 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...