Sciweavers

410 search results - page 56 / 82
» String-to-Dependency Statistical Machine Translation
Sort
View
LREC
2010
119views Education» more  LREC 2010»
14 years 11 months ago
Towards Improving English-Latvian Translation: A System Comparison and a New Rescoring Feature
This paper presents a comparative study of two alternative approaches to statistical machine translation (SMT) and their application to a task of English-to-Latvian translation. F...
Maxim Khalilov, José A. R. Fonollosa, Ingun...
COLING
2010
14 years 4 months ago
Learning Phrase Boundaries for Hierarchical Phrase-based Translation
Hierarchical phrase-based models provide a powerful mechanism to capture non-local phrase reorderings for statistical machine translation (SMT). However, many phrase reorderings a...
Zhongjun He, Yao Meng, Hao Yu
AAAI
2000
14 years 11 months ago
Translating with Scarce Resources
Current corpus-based machine translation techniques do not work very well when given scarce linguistic resources. To examine the gap between human and machine translators, we crea...
Yaser Al-Onaizan, Ulrich Germann, Ulf Hermjakob, K...
LREC
2008
90views Education» more  LREC 2008»
14 years 11 months ago
Word Alignment Annotation in a Japanese-Chinese Parallel Corpus
Parallel corpora are critical resources for machine translation research and development since parallel corpora contain translation equivalences of various granularities. Manual a...
Yujie Zhang, Zhulong Wang, Kiyotaka Uchimoto, Qing...
LREC
2010
169views Education» more  LREC 2010»
14 years 11 months ago
Using Comparable Corpora to Adapt a Translation Model to Domains
Statistical machine translation (SMT) requires a large parallel corpus, which is available only for restricted language pairs and domains. To expand the language pairs and domains...
Hiroyuki Kaji, Takashi Tsunakawa, Daisuke Okada