Sciweavers

96 search results - page 18 / 20
» What's New in Statistical Machine Translation
Sort
View
IPM
2006
171views more  IPM 2006»
13 years 7 months ago
Automatic extraction of bilingual word pairs using inductive chain learning in various languages
In this paper, we propose a new learning method for extracting bilingual word pairs from parallel corpora in various languages. In cross-language information retrieval, the system...
Hiroshi Echizen-ya, Kenji Araki, Yoshio Momouchi
ML
2010
ACM
135views Machine Learning» more  ML 2010»
13 years 2 months ago
Multi-domain learning by confidence-weighted parameter combination
State-of-the-art statistical NLP systems for a variety of tasks learn from labeled training data that is often domain specific. However, there may be multiple domains or sources o...
Mark Dredze, Alex Kulesza, Koby Crammer
MT
2010
100views more  MT 2010»
13 years 6 months ago
Exploiting syntactic relationships in a phrase-based decoder: an exploration
Phrase-based decoding is conceptually simple and straightforward to implement, at the cost of drastically oversimplified reordering models. Syntactically aware models make it pos...
Tim Hunter, Philip Resnik
SAIG
2000
Springer
13 years 11 months ago
Pragmatic Aspects of Reusable Program Generators
When writing a program generator requires considerable intellectual effort, it is valuable to amortize that effort by using the generator to build more than one application. When ...
Norman Ramsey
NIPS
2000
13 years 9 months ago
High-temperature Expansions for Learning Models of Nonnegative Data
Recent work has exploited boundedness of data in the unsupervised learning of new types of generative model. For nonnegative data it was recently shown that the maximum-entropy ge...
Oliver B. Downs