Sciweavers

216 search results - page 35 / 44
» Improvements in Phrase-Based Statistical Machine Translation
Sort
View
EMNLP
2010
14 years 9 months ago
Minimum Error Rate Training by Sampling the Translation Lattice
Minimum Error Rate Training is the algorithm for log-linear model parameter training most used in state-of-the-art Statistical Machine Translation systems. In its original formula...
Samidh Chatterjee, Nicola Cancedda
COLING
2010
14 years 6 months ago
An Empirical Study of Translation Rule Extraction with Multiple Parsers
Translation rule extraction is an important issue in syntax-based Statistical Machine Translation (SMT). Recent studies show that rule coverage is one of the key factors affecting...
Tong Xiao, Jingbo Zhu, Hao Zhang, Muhua Zhu
LREC
2010
150views Education» more  LREC 2010»
15 years 1 months ago
Achieving Domain Specificity in SMT without Overt Siloing
We examine pooling data as a method for improving Statistical Machine Translation (SMT) quality for narrowly defined domains, such as data for a particular company or public entit...
William D. Lewis, Chris Wendt, David Bullock
LREC
2010
169views Education» more  LREC 2010»
15 years 1 months ago
Using Comparable Corpora to Adapt a Translation Model to Domains
Statistical machine translation (SMT) requires a large parallel corpus, which is available only for restricted language pairs and domains. To expand the language pairs and domains...
Hiroyuki Kaji, Takashi Tsunakawa, Daisuke Okada
110
Voted
ACL
2008
15 years 1 months ago
Exploiting N-best Hypotheses for SMT Self-Enhancement
Word and n-gram posterior probabilities estimated on N-best hypotheses have been used to improve the performance of statistical machine translation (SMT) in a rescoring framework....
Boxing Chen, Min Zhang, AiTi Aw, Haizhou Li