This conference builds on ten previous workshops on statistical machine translation:
|Release of training data for shared tasks||January, 2016|
|Evaluation periods for shared tasks||April, 2016|
|Paper submission deadline (Research Papers)||May 8, 2016|
|Paper submission deadline (System Papers)||May 15, 2016|
|Notification of acceptance||June 5, 2016|
|Camera-ready deadline||June 22, 2016|
|Conference in Berlin||August 11-12th, 2016|
This year's conference will feature ten shared tasks:
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:
Registration will be handled by ACL 2016.
The first shared task which will examine translation between the following language pairs:
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 amount to ranking 300 sets of 5 translations, per language pair submitted.
We also provide baseline machine translation systems, with performance comparable to the best systems from last year's shared task.
This task focuses on domain adaptation of MT to the IT domain for the following languages pairs:
Parallel corpora (including in-domain training data) are available. Evaluation will be carried out both automatically and manually. See detailed information about the task.
In this first edition of this task, we will evaluate systems for the translation of scientific abstracts in biological and health sciences for the following languages pairs:
Parallel corpora will be available for the above language pairs but also monoligual corpora for each of the four languages. Evaluation will be carried out both automatically and manually.
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:
In this second edition of the task, the evaluation will focus on one language pair (English-German), measuring systems' capability to reduce the distance (HTER) that separates an automatic translation from its human-revised version approved for publication. This edition will focus on IT domain data, and will provide post-editions (of MT output) collected from professional translators.
Participants in the shared evaluation task will use their automatic evaluation metrics to score the output from the translation task and the tunable metrics task. In addition to MT outputs from the other two tasks, the participants will be provided with reference translations. We will measure the correlation of automatic evaluation metrics with the human judgments.
Quality estimation systems aim at producing an estimate on the quality of a given translation at system run-time, without access to a reference translation. This topic is particularly relevant from a user perspective. Among other applications, it can (i) help decide whether a given translation is good enough for publishing as is; (ii) filter out sentences that are not good enough for post-editing; (iii) select the best translation among options from multiple MT and/or translation memory systems; (iv) inform readers of the target language of whether or not they can rely on a translation; and (v) spot parts (words or phrases) of a translation that are potentially incorrect.
Research on this topic has been showing promising results in the last couple of years. Building on the last three years' experience, the Quality-Estimation track of the WMT15 workshop and shared-task will focus on English, Spanish and German as languages and provide new training and test sets, along with evaluation metrics and baseline systems for variants of the task at three different levels of prediction: word, sentence, and document.
Participants in the tuning task will be given complete Moses models for English-to-Czech and Czech-to-English translation and the standard developments sets from the translation task. The participants are expected to submit the
moses.ini for one or both of the translation directions. We will use the configuration and a fixed revision of Moses to translate official WMT15 test set. The outputs of the various configurations of the system will be scored using the standard manual evaluation procedure.
Pronoun translation poses a problem for current state-of-the-art SMT systems as pronoun systems do not map well across languages, e.g., due to differences in gender, number, case, formality, or humanness, and to differences in where pronouns may be used. Translation divergences typically lead to mistakes in SMT, as when translating the English "it" into French ("il", "elle", or "cela"?) or into German ("er", "sie", or "es"?). One way to model pronoun translation is to treat it as a cross-lingual pronoun prediction task.
We propose such a task, which asks participants to predict a target-language pronoun given a source-language pronoun in the context of a sentence. We further provide a lemmatised target-language human-authored translation of the source sentence, and automatic word alignments between the source sentence words and the target-language lemmata. In the translation, the words aligned to a subset of the source-language third-person pronouns are substituted by placeholders. The aim of the task is to predict, for each placeholder, the word that should replace it from a small, closed set of classes, using any type of information that can be extracted from the documents.
The cross-lingual pronoun prediction task will be similar to the task of the same name at DiscoMT 2015:http://www.idiap.ch/workshop/DiscoMT/shared-task
Participants are invited to submit systems for the English-French and English-German language pairs, for both directions.
Submissions will consist of regular full papers of 6-10 pages, plus additional pages for references, formatted following the ACL 2016 guidelines. 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.
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.
|Subscribe to to the announcement list for WMT by entering your e-mail address below. This list will be used to announce when the test sets are released, to indicate any corrections to the training sets, and to amend the deadlines as needed.|
|You can read past announcements on the Google Groups page for WMT. These also include an archive of announcements from earlier workshops.|
For general questions, comments, etc. please send email
For task-specific questions, please contact the relevant organisers.