56 search results - page 2 / 12 » Finite State Models for the Generation of Large Corpora of N... |
EMNLP
2008
13 years 9 months ago
2008
Traditionally, statistical machine translation systems have relied on parallel bi-lingual data to train a translation model. While bi-lingual parallel data are expensive to genera...
CSL
2007
Springer
13 years 7 months ago
2007
Springer
This study is aimed at investigating whether automatic phonetic transcription procedures can approximate manual transcriptions typically delivered with contemporary large speech c...
ICASSP
2009
IEEE
14 years 2 months ago
2009
IEEE
Performance of n-gram language models depends to a large extent on the amount of training text material available for building the models and the degree to which this text matches...
CICLING
2009
Springer
14 years 8 months ago
2009
Springer
Recent work on the transfer of semantic information across languages has been recently applied to the development of resources annotated with Frame information for different non-En...
EMNLP
2009
13 years 5 months ago
2009
Untranslated words still constitute a major problem for Statistical Machine Translation (SMT), and current SMT systems are limited by the quantity of parallel training texts. Augm...