Sciweavers

295 search results - page 18 / 59
» Combining Outputs from Multiple Machine Translation Systems
Sort
View
EMNLP
2010
14 years 7 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
74
Voted
IRI
2008
IEEE
15 years 4 months ago
Curate a transliteration corpus from transliteration/translation pairs
Transliteration of new named entity is important for information retrieval that crosses two or multiple language. Rule-based machine transliteration is not satisfactory, since dif...
Shih-Hung Wu, Yu-Te Li
CIKM
2011
Springer
13 years 9 months ago
An efficient method for using machine translation technologies in cross-language patent search
Topics in prior-art patent search are typically full patent applications and relevant items are patents often taken from sources in different languages. Cross language patent retr...
Walid Magdy, Gareth J. F. Jones
LREC
2008
155views Education» more  LREC 2008»
14 years 11 months ago
Using Reordering in Statistical Machine Translation based on Alignment Block Classification
Statistical Machine Translation (SMT) is based on alignment models which learn from bilingual corpora the word correspondences between source and target language. These models are...
Marta R. Costa-Jussà, José A. R. Fon...
ICCD
1992
IEEE
84views Hardware» more  ICCD 1992»
15 years 1 months ago
Synthesis of 3D Asynchronous State Machines
We describe a new synthesis procedure for designing asynchronous controllers from burst-mode specifications, a class of specifications allowing multiple input change fundamental m...
Kenneth Y. Yun, David L. Dill, Steven M. Nowick