1255 search results - page 55 / 251 » Information-Based Machine Translation |
126
Voted
LREC
2010
15 years 4 months ago
2010
In Chinese texts, words composed of single or multiple characters are not separated by spaces, unlike most western languages. Therefore Chinese word segmentation is considered an ...
122
Voted
LREC
2008
15 years 4 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 ...
143
Voted
NLE
2007
15 years 2 months ago
2007
We address the problem of extracting bilingual chunk pairs from parallel text to create training sets for statistical machine translation. We formulate the problem in terms of a s...
123
Voted
ACL
2010
15 years 18 days ago
2010
Automatic error detection is desired in the post-processing to improve machine translation quality. The previous work is largely based on confidence estimation using system-based ...
116
Voted
ACL
2011
14 years 6 months ago
2011
This paper presents an attempt at building a large scale distributed composite language model that simultaneously accounts for local word lexical information, mid-range sentence s...