Sciweavers

8 search results - page 1 / 2
» Domain Adaptation for Machine Translation by Mining Unseen W...
Sort
View
ACL
2011
12 years 8 months ago
Domain Adaptation for Machine Translation by Mining Unseen Words
We show that unseen words account for a large part of the translation error when moving to new domains. Using an extension of a recent approach to mining translations from compara...
Hal Daumé III, Jagadeesh Jagarlamudi
LREC
2010
195views Education» more  LREC 2010»
13 years 5 months ago
Adapting Chinese Word Segmentation for Machine Translation Based on Short Units
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 ...
Yiou Wang, Kiyotaka Uchimoto, Jun'ichi Kazama, Can...
LREC
2010
169views Education» more  LREC 2010»
13 years 5 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
EMNLP
2009
13 years 2 months ago
Discriminative Corpus Weight Estimation for Machine Translation
Current statistical machine translation (SMT) systems are trained on sentencealigned and word-aligned parallel text collected from various sources. Translation model parameters ar...
Spyros Matsoukas, Antti-Veikko I. Rosti, Bing Zhan...