Sciweavers

150 search results - page 1 / 30
» Improved Statistical Machine Translation Using Monolingually...
Sort
View
EMNLP
2009
13 years 9 months ago
Improved Statistical Machine Translation Using Monolingually-Derived Paraphrases
Untranslated words still constitute a major problem for Statistical Machine Translation (SMT), and current SMT systems are limited by the quantity of parallel training texts. Augm...
Yuval Marton, Chris Callison-Burch, Philip Resnik
ECAI
2008
Springer
14 years 29 days ago
Improved Statistical Machine Translation Using Monolingual Paraphrases
We propose a novel monolingual sentence paraphrasing method for augmenting the training data for statistical machine translation systems "for free"
Preslav Nakov
ACL
2008
14 years 19 days ago
Combining Multiple Resources to Improve SMT-based Paraphrasing Model
This paper proposes a novel method that exploits multiple resources to improve statistical machine translation (SMT) based paraphrasing. In detail, a phrasal paraphrase table and ...
Shiqi Zhao, Cheng Niu, Ming Zhou, Ting Liu, Sheng ...
EMNLP
2010
13 years 9 months ago
Example-Based Paraphrasing for Improved Phrase-Based Statistical Machine Translation
In this article, an original view on how to improve phrase translation estimates is proposed. This proposal is grounded on two main ideas: first, that appropriate examples of a gi...
Aurélien Max
ACL
2010
13 years 9 months ago
Paraphrase Lattice for Statistical Machine Translation
Lattice decoding in statistical machine translation (SMT) is useful in speech translation and in the translation of German because it can handle input ambiguities such as speech r...
Takashi Onishi, Masao Utiyama, Eiichiro Sumita