NAACL
1994
14 years 25 days ago
1994
To achieve reasonable accuracy in large vocabulary speech recognition systems, it is important to use detailed acoustic models together with good long span language models. For ex...
ACL
2000
14 years 27 days ago
2000
I describe two methods for incorporating information about the relative positions of bilingual word pairs into a Maximum Entropy/Minimum Divergence translation model. The better o...
EMNLP
2007
14 years 29 days ago
2007
Trigram language models are compressed using a Golomb coding method inspired by the original Unix spell program. Compression methods trade off space, time and accuracy (loss). The...
ACL
2008
14 years 1 months ago
2008
We take a multi-pass approach to machine translation decoding when using synchronous context-free grammars as the translation model and n-gram language models: the first pass uses...