Sciweavers

546 search results - page 26 / 110
» Improved Word-Level System Combination for Machine Translati...
Sort
View
IBPRIA
2003
Springer
15 years 2 months ago
Combining Phrase-Based and Template-Based Alignment Models in Statistical Translation
In statistical machine translation, single-word based models have an important deficiency; they do not take contextual information into account for the translation decision. A poss...
Jesús Tomás, Francisco Casacuberta
NAACL
2007
14 years 11 months ago
Source-Language Features and Maximum Correlation Training for Machine Translation Evaluation
We propose three new features for MT evaluation: source-sentence constrained n-gram precision, source-sentence reordering metrics, and discriminative unigram precision, as well as...
Ding Liu, Daniel Gildea
FINTAL
2006
15 years 1 months ago
Statistical Machine Translation of German Compound Words
Abstract. German compound words pose special problems to statistical machine translation systems: the occurence of each of the components in the training data is not sufficient for...
Maja Popovic, Daniel Stein, Hermann Ney
ACL
2010
14 years 7 months ago
Bucking the Trend: Large-Scale Cost-Focused Active Learning for Statistical Machine Translation
We explore how to improve machine translation systems by adding more translation data in situations where we already have substantial resources. The main challenge is how to buck ...
Michael Bloodgood, Chris Callison-Burch
NAACL
2007
14 years 11 months ago
Automatic Evaluation of Machine Translation Based on Rate of Accomplishment of Sub-Goals
The quality of a sentence translated by a machine translation (MT) system is difficult to evaluate. We propose a method for automatically evaluating the quality of each translati...
Kiyotaka Uchimoto, Katsunori Kotani, Yujie Zhang, ...