Abstract This study explores the interaction effect between source text (ST) complexity and machine translation (MT) quality on task difficulty of neural (NMT) post-editing from English to Chinese. When investigating human effort exerted in post-editing, existing studies have seldom taken both ST MT levels into account, mainly focused systems used before emergence NMT. Drawing process product d...

Enthymeme reconstruction, i.e. the task of reformulating arguments with missing propositions, is an exciting task at the borderline of text understanding and argument interpretation. However, there is some doubt in the community about the feasibility of this task due to the wide range of possible reformulations that are open to humans. We therefore believe that research on how to define an obje...

Real-time collaborative editors, like GoogleDocs or Etherpad, allow the simultaneous edition of adocument by several users. These applications need to replicate the edited document, for the so calledreal-time purpose of permitting a fast and reactive editing by any user at any time. Editing conflictsfrequently occur, and must be automatically handled by the application, in order to ...

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...