Paper: Enabling Monolingual Translators: Post-Editing vs. Options

ACL ID N10-1078
Title Enabling Monolingual Translators: Post-Editing vs. Options
Venue Human Language Technologies
Session Main Conference
Year 2010

We carried out a study on monolingual trans- lators with no knowledge of the source lan- guage, but aided by post-editing and the dis- play of translation options. On Arabic-English and Chinese-English, using standard test data and current statistical machine translation sys- tems, 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 docu- ments. While machine translation systems have advanced greatly over the last decade, nobody seriously ex- pects human-level performance any time soon, ex- cept for very constraint settings. But are todays systems good enough to enable monolingual speak- ers of the target language without knowledge o...