4 search results - page 1 / 1 » A Hybrid Morpheme-Word Representation for Machine Translatio... |
EMNLP
2010
13 years 2 months ago
2010
We propose a language-independent approach for improving statistical machine translation for morphologically rich languages using a hybrid morpheme-word representation where the b...
TASLP
2008
13 years 4 months ago
2008
Language modeling for an inflected language such as Arabic poses new challenges for speech recognition and machine translation due to its rich morphology. Rich morphology results i...
ACL
2010
13 years 2 months ago
2010
We illustrate and explain problems of n-grams-based machine translation (MT) metrics (e.g. BLEU) when applied to morphologically rich languages such as Czech. A novel metric SemPO...
ACL
2006
13 years 6 months ago
2006
Statistical machine translation is quite robust when it comes to the choice of input representation. It only requires consistency between training and testing. As a result, there ...