PHRASE AND NGRAM-BASED STATISTICAL MACHINE TRANSLATION SYSTEM COMBINATION

Multiples translations can be computed by one machine translation (MT) system or by different MT systems. We may assume that different MT systems make different errors due to using different models, generation strategies, or tweaks. An investigated technique, inherited from automatic speech recognit...

Full description

Saved in:
Bibliographic Details
Published inApplied artificial intelligence Vol. 23; no. 7; pp. 694 - 711
Main Authors Costa-Jussà, Marta R., Fonollosa, José A. R.
Format Journal Article
LanguageEnglish
Published Philadelphia Taylor & Francis Group 31.07.2009
Taylor & Francis Ltd
Subjects
Algorithms
Artificial intelligence
Information systems
Translations
Voice recognition
Online AccessGet full text

Cover

More Information
Summary:Multiples translations can be computed by one machine translation (MT) system or by different MT systems. We may assume that different MT systems make different errors due to using different models, generation strategies, or tweaks. An investigated technique, inherited from automatic speech recognition (ASR), is the so-called system combination that is based on combining the outputs of multiples MT systems. We combine the outputs of a phrase- and Ngram-based Statistical MT (SMT) systems using statistical criteria and additional rescoring features.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0883-9514
1087-6545
DOI:10.1080/08839510903207890