Sciweavers

1053 search results - page 25 / 211
» Learning Rules to Improve a Machine Translation System
Sort
View
ICAC
2005
IEEE
14 years 1 months ago
PICCIL: Interactive Learning to Support Log File Categorization
Motivated by the real-world application of categorizing system log messages into defined situation categories, this paper describes an interactive text categorization method, PICC...
David Loewenstern, Sheng Ma, Abdi Salahshour
ACL
2011
12 years 11 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
ACL
1998
13 years 8 months ago
Maximum Entropy Model Learning of the Translation Rules
This paper proposes a learning method of translation rules from parallel corpora. This method applies the maximum entropy principle to a probabilistic model of translation rules. ...
Kengo Sato, Masakazu Nakanishi
NAACL
2010
13 years 5 months ago
Improved Models of Distortion Cost for Statistical Machine Translation
The distortion cost function used in Mosesstyle machine translation systems has two flaws. First, it does not estimate the future cost of known required moves, thus increasing sea...
Spence Green, Michel Galley, Christopher D. Mannin...
ACL
2010
13 years 5 months ago
Discriminative Modeling of Extraction Sets for Machine Translation
We present a discriminative model that directly predicts which set of phrasal translation rules should be extracted from a sentence pair. Our model scores extraction sets: nested ...
John DeNero, Dan Klein