Sciweavers

120 search results - page 17 / 24
» Boosting-Based System Combination for Machine Translation
Sort
View
COLING
1990
13 years 8 months ago
Morphological Analysis and Synthesis by Automated Discovery and Acquisition of Linguistic Rules
':[his paper describes a rule-based machine learning approach to morphological processing in the system called XMAS. XMAS discovers and acquires linguistic rules from example...
Byoung-Tak Zhang, Yung Taek Kim
TREC
2000
13 years 9 months ago
TREC-9 CLIR at CUHK: Disambiguation by Similarity Values Between Adjacent Words
We investigated the dictionary-based query translation method combining the translation disambiguation process using statistic cooccurrence information trained from the provided c...
Honglan Jin, Kam-Fai Wong
COLING
2000
13 years 9 months ago
The Week at a Glance - Cross-language Cross-document Information Extraction and Translation
Work on the production of texts in English describing instances of a particular event type from multiple news sources will be described. A system has been developed which extracts...
James R. Cowie, Yevgeny Ludovik, Hugo Molina-Salga...
ACL
2008
13 years 9 months ago
Exploiting N-best Hypotheses for SMT Self-Enhancement
Word and n-gram posterior probabilities estimated on N-best hypotheses have been used to improve the performance of statistical machine translation (SMT) in a rescoring framework....
Boxing Chen, Min Zhang, AiTi Aw, Haizhou Li
ACL
2006
13 years 9 months ago
Minimum Risk Annealing for Training Log-Linear Models
When training the parameters for a natural language system, one would prefer to minimize 1-best loss (error) on an evaluation set. Since the error surface for many natural languag...
David A. Smith, Jason Eisner