This paper presents the results of the WMT15 shared tasks, which included a standard news translation task, a metrics task, a tuning task, a task for run-time estimation of machine translation quality, and an automatic post-editing task. This year, 68 machine translation systems from 24 institutions were submitted to the ten translation directions in the standard translation task. An additional...

With the noticeable improvement in the overall quality of Machine Translation (MT) systems in recent years, post-editing of MT output is starting to become a common practice among human translators. However, it is well known that the quality of a given MT system can vary significantly across translation segments and that post-editing bad quality translations is a tedious task that may require m...

This paper presents the LIG-CRIStAL submission to the shared Automatic PostEditing task of WMT 2017. We propose two neural post-editing models: a monosource model with a task-specific attention mechanism, which performs particularly well in a low-resource scenario; and a chained architecture which makes use of the source sentence to provide extra context. This latter architecture manages to sli...

This paper describes an automated postediting submission to the DiscoMT 2015 shared task on pronoun translation. Postediting is achieved by applying pronounspecific rules to the output of an Englishto-French phrase-based SMT system.

Distributed, collaborative editing of documents in a synchronous manner is increasingly becoming a very common and highly necessary task. It is, therefore, crucial to produce extremely easy-to-use editors facilitating this document-centered task. Providing awareness is a vital feature enhancing the usability of real-time cooperative document editing systems. Document-related awareness provides ...

While machine translation is sometimes sufficient for conveying information across language barriers, many scenarios still require precise human-quality translation that MT is currently unable to deliver. Governments and international organizations such as the United Nations require accurate translations of content dealing with complex geopolitical issues. Community-driven projects such as Wiki...

This paper examines the linguistic realization of continuative and contrastive discourse relations (DRs) in English argumentative discourse, focusing on both as product process. Based a corpus 25 texts with corresponding experimental data stemming from an editing-based task, this study aims to answer questions (i) how DRs are linguistically realized (i.e., encoded coherence strands or additiona...

This paper describes the two systems submitted by LIMSI to the WMT’15 Shared Task on Automatic Post-Editing. The first one relies on a reformulation of the APE task as a Machine Translation task; the second implements a simple rule-based approach. Neither of these two systems manage to improve the automatic translation. We show, by carefully analyzing the failure of our systems that this counte...

Professional document editing tools require a certain level of expertise to perform complex edit operations. To make accessible increasingly novice users, we investigate intelligent assistant systems that can or suggest edits based on user's natural language request. Such system should be able understand the ambiguous requests and contextualize them visual cues textual content found in image lo...

The cognitive task analysis has been of great importance in the design of man-machine systems and working environment with the widespread use of computerized systems. This article introduces the Information Flow Modeling[5] as a potential tool for the cognitive task analysis. Using this modeling technique, the human activities during the task are modeled in detail as information ows along with ...