803 search results - page 17 / 161 » Cognates Can Improve Statistical Translation Models |
ACL
2008
13 years 10 months ago
2008
Large-scale discriminative machine translation promises to further the state-of-the-art, but has failed to deliver convincing gains over current heuristic frequency count systems....
ACL
2010
13 years 6 months ago
2010
Tree-to-string systems (and their forestbased extensions) have gained steady popularity thanks to their simplicity and efficiency, but there is a major limitation: they are unable...
NAACL
2007
13 years 10 months ago
2007
This paper presents a maximum entropy machine translation system using a minimal set of translation blocks (phrase-pairs). While recent phrase-based statistical machine translatio...
EMNLP
2008
13 years 10 months ago
2008
Minimum-error-rate training (MERT) is a bottleneck for current development in statistical machine translation because it is limited in the number of weights it can reliably optimi...
EMNLP
2007
13 years 10 months ago
2007
It is possible to reduce the bulk of phrasetables for Statistical Machine Translation using a technique based on the significance testing of phrase pair co-occurrence in the para...