Sciweavers

127 search results - page 11 / 26
» System Combination for Machine Translation of Spoken and Wri...
Sort
View
ACL
2007
13 years 10 months ago
Machine Translation by Triangulation: Making Effective Use of Multi-Parallel Corpora
Current phrase-based SMT systems perform poorly when using small training sets. This is a consequence of unreliable translation estimates and low coverage over source and target p...
Trevor Cohn, Mirella Lapata
INTERSPEECH
2010
13 years 3 months ago
Combining many alignments for speech to speech translation
Alignment combination (symmetrization) has been shown to be useful for improving Machine Translation (MT) models. Most existing alignment combination techniques are based on heuri...
Sameer Maskey, Steven J. Rennie, Bowen Zhou
LREC
2010
178views Education» more  LREC 2010»
13 years 10 months ago
Data Issues in English-to-Hindi Machine Translation
Statistical machine translation to morphologically richer languages is a challenging task and more so if the source and target languages differ in word order. Current state-of-the...
Ondrej Bojar, Pavel Stranák, Daniel Zeman
ACL
2008
13 years 10 months ago
Decompounding query keywords from compounding languages
Splitting compound words has proved to be useful in areas such as Machine Translation, Speech Recognition or Information Retrieval (IR). Furthermore, real-time IR systems (such as...
Enrique Alfonseca, Slaven Bilac, Stefan Pharies
COLING
2010
13 years 3 months ago
Urdu and Hindi: Translation and sharing of linguistic resources
Hindi and Urdu share a common phonology, morphology and grammar but are written in different scripts. In addition, the vocabularies have also diverged significantly especially in ...
Karthik Visweswariah, Vijil Chenthamarakshan, Nand...