Download | - View accepted manuscript: Automatic Detection of Translated Text and its Impact on Machine Translation (PDF, 544 KiB)
|
---|
Author | Search for: Kurokawa, David1; Search for: Goutte, Cyril1; Search for: Isabelle, Pierre1 |
---|
Affiliation | - National Research Council of Canada. NRC Institute for Information Technology
|
---|
Format | Text, Article |
---|
Conference | MT Summit XII, The twelfth Machine Translation Summit International Association for Machine Translation hosted by the Association for Machine Translation in the Americas, Ottawa, Ontario, August 26-30, 2009 |
---|
Abstract | We investigate the possibility of automatically detecting whether a piece of text is an original or a translation. On a large parallel English-French corpus where reference information is available, we find that this is possible with around 90% accuracy. We further study the implication this has on Machine Translation performance. After separating our corpus according to translation direction, we train direction-specific phrase-based MT systems and show that they yield improved translation performance. This suggests that taking directionality into account when training SMT systems may have a significant effect on output quality. |
---|
Publication date | 2009 |
---|
In | |
---|
Language | English |
---|
Peer reviewed | Yes |
---|
NPARC number | 16335045 |
---|
Export citation | Export as RIS |
---|
Report a correction | Report a correction (opens in a new tab) |
---|
Record identifier | 335e44df-2f0a-47b4-be0f-f59e3e00f1a4 |
---|
Record created | 2010-11-05 |
---|
Record modified | 2020-04-16 |
---|