This conference builds on a series of annual workshops and conferences on statistical machine translation, going back to 2006:

• the NAACL-2006 Workshop on Statistical Machine Translation,
• the ACL-2007 Workshop on Statistical Machine Translation,
• the ACL-2008 Workshop on Statistical Machine Translation,
• the EACL-2009 Workshop on Statistical Machine Translation,
• the ACL-2010 Workshop on Statistical Machine Translation
• the EMNLP-2011 Workshop on Statistical Machine Translation,
• the NAACL-2012 Workshop on Statistical Machine Translation,
• the ACL-2013 Workshop on Statistical Machine Translation,
• the ACL-2014 Workshop on Statistical Machine Translation,
• the EMNLP-2015 Workshop on Statistical Machine Translation,
• the First Conference on Machine Translation (at ACL-2016).
• the Second Conference on Machine Translation (at EMNLP-2017).

IMPORTANT DATES

OVERVIEW

This year's conference will feature the following shared tasks:

• a news translation task
• a biomedical translation task ,
• an automatic post-editing task,
• a metrics task (assess MT quality given reference translation).
• a quality estimation task (assess MT quality without access to any reference),
• a multimodal translation task

In addition to the shared tasks, the conference will also feature scientific papers on topics related to MT. Topics of interest include, but are not limited to:

• MT models (neural, statistical etc. )
• analysis of neural models for MT
• using comparable corpora for MT
• selection and preparation of training data for MT
• incorporating linguistic information into MT
• decoding
• system combination
• error analysis
• manual and automatic methods for evaluating MT
• quality estimation for MT

REGISTRATION AND VISA INFORMATION

NEWS TRANSLATION TASK

This shared task will examine translation between the following language pairs:

• English-Chinese and Chinese-English
• English-Czech and Czech-English
• English-Estonian and Estonian-English
• English-Finnish and Finnish-English
• English-German and German-English
• English-Kazakh and Kazakh-English
• English-Russian and Russian-English
• English-Turkish and Turkish-English

NB: The Kazakh task is postponed (probably until WMT19)

All participants who submit entries will have their translations evaluated. We will evaluate translation performance by human judgment. To facilitate the human evaluation we will require participants in the shared tasks to manually judge some of the submitted translations. For each team, this will be about 8 hours per language pair submitted.

For 2018 we highlight the following innovations in the news task:

Language pairs

This year we introduce Estonian to/from English and Kazakh to/from English as additional language pairs.

NEW: Multilinguality

We encourage participants to exploit multilingual training resources. In other words, to use other languages and third languages to improve translation, for example, participants could exploit the similarity of Finnish and Estonian, or make use of the Russian-Kazakh data set that we will release.

NEW: Unsupervised learning

We also encourage the more adventurous participants to avoid the parallel corpora and use only monolingual corpora only to train the translation models. Use cross-lingual embeddings, or see the news translation task for more ideas.

NEW: Deep analysis through additional test sets

At no additional burden on the News Translation Task participants (aside from having to translate much larger input data), we will collectively provide a deeper analysis of various qualities of the translations.

For more information or if you would like to join this activity, see the WMT18 Addtitional Test Suites Google doc.

BIOMEDICAL TRANSLATION TASK

In this third edition of this task, we will evaluate systems for the translation of biomedical documents for the following languages pairs:

• English-French and French-English
• English-Portuguese and Portuguese-English
• English-Spanish and Spanish-English
• English-German and German-English
• English-Chinese and Chinese-English NEW
• TBD

Parallel corpora will be available for all language pairs but also monoligual corpora for some languages. Evaluation will be carried out both automatically and manually.

AUTOMATIC POST-EDITING TASK

This shared task will examine automatic methods for correcting errors produced by machine translation (MT) systems. Automatic Post-editing (APE) aims at improving 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

In this fourth edition of the task, the evaluation will focus on two subtasks:

• English-German (IT domain), with MT segments produced by a phrase-based system
• English-German (IT domain), with MT segments produced by a neural system

METRICS TASK

QUALITY ESTIMATION TASK

MULTIMODAL TRANSLATION TASK

PAPER SUBMISSION INFORMATION

Submissions will consist of regular full papers of 6-10 pages, plus additional pages for references, formatted following the EMNLP 2018 guidelines. Supplementary material can be added to research papers. In addition, shared task participants will be invited to submit short papers (suggested length: 4-6 pages, plus references) describing their systems or their evaluation metrics. Both submission and review processes will be handled electronically. Note that regular papers must be anonymized, while system descriptions do not need to be.

Research papers that have been or will be submitted to other meetings or publications must indicate this at submission time, and must be withdrawn from the other venues if accepted and published at WMT 2018. We will not accept for publication papers that overlap significantly in content or results with papers that have been or will be published elsewhere. It is acceptable to submit work that has been made available as a technical report (or similar, e.g. in arXiv) without citing it. This double submission policy only applies to research papers, so system papers can have significant overlap with other published work, if it is relevant to the system description.

We encourage individuals who are submitting research papers to evaluate their approaches using the training resources provided by this conference and past workshops, so that their experiments can be repeated by others using these publicly available corpora.

POSTER FORMAT

ANNOUNCEMENTS

You can read past announcements on the Google Groups page for WMT. These also include an archive of announcements from earlier workshops.

INVITED TALK

ORGANIZERS

PROGRAM COMMITTEE

ANTI-HARASSMENT POLICY

WMT follows the ACL's anti-harassment policy

CONTACT

For general questions, comments, etc. please send email to bhaddow@inf.ed.ac.uk.
For task-specific questions, please contact the relevant organisers.

ACKNOWLEDGEMENTS