论文信息 - Enabling Monolingual Translators: Post-Editing vs. Options

Enabling Monolingual Translators: Post-Editing vs. Options

We carried out a study on monolingual translators with no knowledge of the source language, but aided by post-editing and the display of translation options. On Arabic-English and Chinese-English, using standard test data and current statistical machine translation systems, 10 monolingual translators were able to translate 35% of Arabic and 28% of Chinese sentences correctly on average, with some of the participants coming close to professional bilingual performance on some of the documents.

Philipp Koehn | Philipp Koehn

[1] Philipp Koehn,et al. Findings of the 2009 Workshop on Statistical Machine Translation , 2009, WMT@EACL.

[2] George F. Foster,et al. TransType: a Computer-Aided Translation Typing System , 2000 .

[3] K. Saravanan,et al. wikiBABEL: community creation of multilingual data , 2008, Int. Sym. Wikis.

[4] Philipp Koehn,et al. Moses: Open Source Toolkit for Statistical Machine Translation , 2007, ACL.

[5] Philipp Koehn,et al. A Web-Based Interactive Computer Aided Translation Tool , 2009, ACL.

[6] Philipp Koehn,et al. Proceedings of the Fourth Workshop on Statistical Machine Translation, WMT@EACL 2009, Athens, Greece, March 30-31, 2009 , 2009, WMT@EACL.

[7] G. Elisabeta Marai,et al. Correcting Automatic Translations through Collaborations between MT and Monolingual Target-\-Lan\-gua\-ge Users , 2009, EACL.

[8] Barry Haddow,et al. Interactive Assistance to Human Translators using Statistical Machine Translation Methods , 2009, MTSUMMIT.

[9] Chris Callison-Burch. Linear B System Description for the 2005 NIST MT Evaluation Exercise , 2005 .

[10] Hermann Ney,et al. Statistical Approaches to Computer-Assisted Translation , 2009, CL.