Cross-lingual Pronoun Prediction Shared Task

Event Notification Type: 
Call for Participation
Abbreviated Title: 
DiscoMT 2017 Shared Task
Location: 
Copenhagen
Friday, 8 September 2017
State: 
Country: 
Denmark
City: 
Copenhagen
Contact: 
Sharid Loáiciga
Jörg Tiedemann
Submission Deadline: 
Friday, 9 June 2017

=============================================================
DEADLINE EXTENSION
=============================================================

Website: https://www.idiap.ch/workshop/DiscoMT/shared-task

Due to the multiple shared tasks organized this year (CONLL, WMT, RepEval, SemEval, CORBON, ...), our initial timeline resulted very tight for many interested participants. In this light, we have decided to extend our deadline once again.

NEW! System submission AND system papers: 9th of June
NEW! Release of results: 16th June
30 June 2017 Notification of acceptance
14 July 2017 Camera-ready papers due
September 2017 DiscoMT 2017 workshop in Copenhagen (in conjunction with EMNLP)

=============================================================
2017 DiscoMT Shared Task on Cross-lingual Pronoun Prediction
=============================================================

The cross-lingual pronoun prediction task concerns (discourse-aware) machine translation, anaphora resolution and machine learning in general.

Participants are asked to predict a target-language pronoun given a source-language pronoun in the context of a sentence. For example, in the English-French sub-task, to predict the correct translation of "it" or "they" into French (ce, elle, elles, il, ils, cela, on, OTHER). You may use any type of information that can be extracted from the documents. We provide training and development data and a simple baseline system using an N-gram language model.

Participants are invited to submit systems for:

English-French
English-German
Spanish-English
German-English

More details can be found on our website: https://www.idiap.ch/workshop/DiscoMT/shared-task

Feel free to ask any questions you may have about the shared task!
https://groups.google.com/forum/#!forum/discomt2017-cross-lingual-pronou...

-------------------------------------------------------------------------
Acknowledgements:
The organisation of this task has received support from the following project: Discourse-Oriented Statistical Machine Translation funded by the Swedish Research Council (2012-916)
-------------------------------------------------------------------------