*CALL FOR PARTICIPATION*

*in the*

*eight Automatic Post-Editing (APE) shared task *

*at the seventh Conference on Machine Translation (WMT22)*



*OVERVIEW*

The 8th round of the APE shared task follows the success of the previous
rounds organized from 2015 to 2021. The aim is to examine *automatic
methods for correcting errors produced by an unknown machine translation
(MT) system.* This must be done by exploiting knowledge acquired from human
post-edits, which are provided as training material.

*Goals*

The aim of this 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

*Task Description*

This year the language setting shifts to Indian languages focusing on *English
--> Marathi* language pair. The provided data cover several domains
like *healthcare,
tourism, general/news*.

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

*DIFFERENCES FROM THE PREVIOUS ROUND (WMT 2021)*

Compared to the previous round, the main differences are:

   - Focus on Indian language (Marathi) as target language
   - Use of new domains healthcare and tourism for the selected target
   language

*Important dates*

Release of training and development data

May 17, 2022

Release of test data

July 11, 2022

APE system submission deadline

July 18, 2022

Manual evaluation

August

Paper submission deadline

September 7, 2022

Notification of acceptance

October 9, 2022

Camera-ready deadline

October 16, 2022



Further information about the shared task is available here
<https://www.statmt.org/wmt22/ape-task.html>

-- 
On behalf of
the APE shared task organizers
_______________________________________________
Moses-support mailing list
Moses-support@mit.edu
https://mailman.mit.edu/mailman/listinfo/moses-support

Reply via email to