59 search results - page 9 / 12 » Diversify and Combine: Improving Word Alignment for Machine ... |
IUCS
2009
ACM
14 years 2 months ago
2009
ACM
This paper proposes a new approach for the automatic extraction of bilingual terms from a domain-specific bilingual parallel corpus. We combine existing monolingual term extractor...
NAACL
2010
13 years 5 months ago
2010
The distortion cost function used in Mosesstyle machine translation systems has two flaws. First, it does not estimate the future cost of known required moves, thus increasing sea...
ACL
2007
13 years 9 months ago
2007
Data sparseness is one of the factors that degrade statistical machine translation (SMT). Existing work has shown that using morphosyntactic information is an effective solution t...
ACL
2008
13 years 9 months ago
2008
We improve the quality of statistical machine translation (SMT) by applying models that predict word forms from their stems using extensive morphological and syntactic information...
EMNLP
2009
13 years 5 months ago
2009
Current statistical machine translation (SMT) systems are trained on sentencealigned and word-aligned parallel text collected from various sources. Translation model parameters ar...