We moved to Seattle! We packed our bags and headed north to become the University of Washington Interactive Data Lab. Come visit us...

The Efficacy of Human Post-Editing for Language Translation

Spence Green, Jeffrey Heer, Christopher D. Manning
Translation as post-editing. (a) Mouse hover events over the source sentence. The color and area of the circles indicate part of speech and mouse hover frequency, respectively, during translation to French. Nouns (blue) seem to be significant. (b) The user corrects two spans in the MT output to produce a final translation.


Language translation is slow and expensive, so various forms of machine assistance have been devised. Automatic machine translation systems process text quickly and cheaply, but with quality far below that of skilled human translators. To bridge this quality gap, the translation industry has investigated post-editing, or the manual correction of machine output. We present the first rigorous, controlled analysis of post-editing and find that post-editing leads to reduced time and, surprisingly, improved quality for three diverse language pairs (English to Arabic, French, and German). Our statistical models and visualizations of experimental data indicate that some simple predictors (like source text part of speech counts) predict translation time, and that post-editing results in very different interaction patterns. From these results we distill implications for the design of new language translation interfaces.

materials and links


Spence Green, Jeffrey Heer, Christopher D. Manning
ACM Human Factors in Computing Systems (CHI), 2013
PDF (2.3 MB) | Best Paper Award