LINGUIST List 28.1467
Thu Mar 23 2017
Calls: Computational Linguistics/Denmark
Editor for this issue: Kenneth Steimel <kenlinguistlist.org>
Preslav Nakov <preslav.nakov
EMNLP 2017 3rd Workshop on Discourse in Machine Translation E-mail this message to a friend
Full Title: EMNLP 2017 3rd Workshop on Discourse in Machine Translation
Short Title: DiscoMT
Date: 08-Sep-2017 - 08-Sep-2017
Location: Copenhagen, Denmark
Contact Person: Preslav Nakov
Meeting Email: < click here to access email >
Web Site: https://www.idiap.ch/workshop/DiscoMT
Linguistic Field(s): Computational Linguistics
Call Deadline: 02-May-2017
The third workshop on Discourse in MT, a sattelite workshop of EMNLP 2017, follows up from the ACL 2013 DiscoMT and the EMNLP 2015 DiscoMT workshops. As in the first two editions, the 2017 workshop will focus on language processing techniques, whether theoretically-inspired or empirical, which address one or more discourse-level phenomena in combination with MT or from a cross-lingual perspective.The goal is to present methods and software that enhance the capabilities of MT systems on discourse-level phenomena, but also studies that assess the quantity and origins of MT difficulties with discourse, including for research and commercial MT systems.
DiscoMT 2017 includes a shared task on pronoun translation, composed of two sub-tasks: cross-lingual pronoun prediction, and pronoun translation. These are a follow up of the DiscoMT 2015 and the WMT 2016 shared tasks.
Call for Participation:
DiscoMT 2017 Shared Task on Cross-lingual Pronoun Prediction
At the 3rd Workshop on Discourse in Machine Translation (collocated with EMNLP 2017)
We are pleased to announce an exciting cross-lingual pronoun prediction task for people interested in (discourse-aware) machine translation, anaphora resolution and machine learning in general.
In the cross-lingual pronoun prediction task, 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-to-French sub-task, to predict the correct translation of ''it'' or ''they'' into French (ce, elle, elles, il, ils, ça, 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 the English-French and English-German, German-English and Spanish-English language pairs.
More details can be found below, and on our website: https://www.idiap.ch/workshop/DiscoMT/shared-task
March 2017: Release of training data
2 May 2017: Release of test data
9 May 2017: System submission deadline
15 May 2017: Release of results
9 June 2017: System paper submission deadline
30 June 2017: Notification of acceptance
14 July 2017: Camera-ready papers due
Discussion group: https://groups.google.com/forum/#!forum/discomt2017-cross-lingual-pronoun-prediction-shared-task
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)
Page Updated: 23-Mar-2017