Backtranslation Feedback Improves User Confidence in MT, Not Quality
This addresses the user experience gap in outbound translation for authors translating into unknown languages, but it is incremental as it builds on existing feedback methods without major breakthroughs.
The study tackled the problem of improving user experience in outbound translation (e.g., English to Czech/Estonian) by testing feedback methods like backward translation, quality estimation, and source paraphrasing, finding that backward translation increased user confidence but not objective translation quality.
Translating text into a language unknown to the text's author, dubbed outbound translation, is a modern need for which the user experience has significant room for improvement, beyond the basic machine translation facility. We demonstrate this by showing three ways in which user confidence in the outbound translation, as well as its overall final quality, can be affected: backward translation, quality estimation (with alignment) and source paraphrasing. In this paper, we describe an experiment on outbound translation from English to Czech and Estonian. We examine the effects of each proposed feedback module and further focus on how the quality of machine translation systems influence these findings and the user perception of success. We show that backward translation feedback has a mixed effect on the whole process: it increases user confidence in the produced translation, but not the objective quality.