39 search results - page 6 / 8 » Tuning statistical machine translation parameters using perp... |
COLING
2000
13 years 8 months ago
2000
Multi-word terms are traditionally identified using statistical techniques or, more recently, using hybrid techniques combining statistics with shallow linguistic information. Al)...
ACL
2009
13 years 5 months ago
2009
Minimum Error Rate Training (MERT) and Minimum Bayes-Risk (MBR) decoding are used in most current state-of-theart Statistical Machine Translation (SMT) systems. The algorithms wer...
ICASSP
2010
IEEE
13 years 7 months ago
2010
IEEE
This paper presents the use of online Variational Bayes method for online Voice Activity Detection (VAD) in an unsupervised context. In conventional VAD, the final step often rel...
EMNLP
2010
13 years 5 months ago
2010
A word in one language can be translated to zero, one, or several words in other languages. Using word fertility features has been shown to be useful in building word alignment mo...
EMNLP
2009
13 years 5 months ago
2009
Minimum error rate training (MERT) involves choosing parameter values for a machine translation (MT) system that maximize performance on a tuning set as measured by an automatic e...