[Corpora-List] CfP to the Automatic Post-Editing shared task at WMT18

Rajen Chatterjee rajen.k.chatterjee at gmail.com
Sun Feb 18 18:27:40 CET 2018

(Apologizes for cross posting)


in the

Fourth Automatic Post-Editing (APE) shared task

at the Third Conference on Machine Translation (WMT18)



The fourth round of the APE shared task follows the success of the previous three rounds organised in 2015, 2016 and 2017. The aim is to examine automatic methods for correcting errors produced by an unknown machine translation (MT) system. This has to be done by exploiting knowledge acquired from human post-edits, which are provided as training material.

Similar to the last round, this year the task focuses on Information Technology domain for English-German language direction. One novelty, however, is represented by the addition of one MT system: this year, the task will hence cover MT output generated by a phrase-based system (PBSMT), and a neural MT system (NMT). In both cases, the source sentences have been translated into the target language by an MT system unknown to the participants (in terms of system configuration) and then manually post-edited by professional translators.

At training stage, the collected human post-edits have to be used to learn correction rules for the APE systems. At test stage they will be used for system evaluation with automatic metrics (TER and BLEU).



The aim of the APE task is to improve MT output in black-box scenarios, in which the MT system is used "as is" and cannot be modified. From the application point of view, APE components would make it possible to:


Cope with systematic errors of an MT system whose decoding process is

not accessible;


Provide professional translators with improved MT output quality to

reduce (human) post-editing effort;


Adapt the output of a general-purpose system to the lexicon/style

requested in a specific application domain.



Training, development and test data consist in English-German triplets (source, target, and post-edit) belonging to the IT domain, and are already tokenized. All data is provided by the EU project QT21 (http://www.qt21.eu/ ).

Systems' performance will be evaluated with respect to their capability to reduce the distance that separates an automatic translation from its human-revised version. Such distance will be measured in terms of TER, which will be computed between automatic and human post-edits in case-sensitive mode. Also BLEU will be taken into consideration as a secondary evaluation metric.

To gain further insights on final output quality, a subset of the outputs of the submitted systems will also be manually evaluated.



Compared to the the thrid round, the main differences are:

- Larger data set. (the eSCAPE corpus)

- Additional MT system (Neural-based);



Release of training data February 16, 2018 Release of test data May 4, 2018 Submission deadline June 4, 2018 Paper submission deadline July 27, 2018 (TBC) Manual evaluation TBD Notification of acceptance August 18, 2018 (TBC) Camera-ready deadline August 31, 2018 (TBC)

-- On behalf of The APE task organizers -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 11800 bytes Desc: not available URL: <https://www.uib.no/mailman/public/corpora/attachments/20180218/97f1b0e4/attachment.txt>

More information about the Corpora mailing list