Permanent URL to this publication: http://dx.doi.org/10.5167/uzh-63326
Fishel, Mark; Bojar, Ondřej; Popovic, Maja (2012). Terra: a collection of translation error-annotated corpora. In: The 8th international conference on Language Resources and Evaluation (LREC), Istanbul, Turkey, 21 May 2012 - 27 May 2012, 7-14.
Recently the first methods of automatic diagnostics of machine translation have emerged; since this area of research is relatively young, the efforts are not coordinated. We present a collection of translation error-annotated corpora, consisting of automatically produced translations and their detailed manual translation error analysis. Using the collected corpora we evaluate the available state-of-the-art methods of MT diagnostics and assess, how well the methods perform, how they compare to each other and whether they can be useful in practice.
|Item Type:||Conference or Workshop Item (Paper), refereed, original work|
|Communities & Collections:||06 Faculty of Arts > Institute of Computational Linguistics|
|DDC:||000 Computer science, knowledge & systems|
|Event End Date:||27 May 2012|
|Deposited On:||13 Jul 2012 09:09|
|Last Modified:||18 Oct 2012 19:25|
|Free access at:||Official URL. An embargo period may apply.|
Users (please log in): suggest update or correction for this item
Repository Staff Only: item control page