51 search results - page 8 / 11 » Automatic Filtering of Bilingual Corpora for Statistical Mac... |
LREC
2008
13 years 9 months ago
2008
In current phrase-based Statistical Machine Translation systems, more training data is generally better than less. However, a larger data set eventually introduces a larger model ...
ACL
2010
13 years 5 months ago
2010
The pipeline of most Phrase-Based Statistical Machine Translation (PB-SMT) systems starts from automatically word aligned parallel corpus. But word appears to be too fine-grained ...
ACL
2008
13 years 9 months ago
2008
In statistical language modeling, one technique to reduce the problematic effects of data sparsity is to partition the vocabulary into equivalence classes. In this paper we invest...
COLING
2010
13 years 2 months ago
2010
This paper1 presents an empirical approach to mining parallel corpora. Conventional approaches use a readily available collection of comparable, nonparallel corpora to extract par...
ECIR
2010
Springer
13 years 9 months ago
2010
Springer
We present two methods for estimating replacement probabilities without using parallel corpora. The first method proposed exploits the possible translation probabilities latent in ...