This paper discusses multilingual document authoring, viewed as providing computer support for a user to author a document in some source language while automatically generating the same content in one or many target languages. A kind of unanticipated use of multilingual authoring appeared in the service sector, in situations where an employee is servicing customers by answering their requests, or helping them, via written electronic communication. Decoupling the employee’s language from the customer’s language may open up new perspectives and motivated this work, where we propose a small set of extensions to be made on a translation memory to support multilingual authoring more efficiently. We describe how an instance of such extended formalism can be conveniently created thanks to a domain specific language and describe how we implemented a full system. Finally, we report on the experiment we ran in a real business setting.
Extended Translation Memories for Multilingual Document Authoring
| Jean-Luc Meunier, Marc Dymetman |
| BUCC, 7th Workshop on Building and Using Comparable Corpora, Reykjavik Iceland, 27 May 2014. |
The research we conduct on expressive visual representations is applicable to visual search, object detection, image classification and the automatic extraction of 3D human poses and shapes that can be used for human behavior understanding and prediction, human-robot interaction or even avatar animation. We also extract 3D information from images that can be used for intelligent robot navigation, augmented reality and the 3D reconstruction of objects, buildings or even entire cities.
Our work covers the spectrum from unsupervised to supervised approaches, and from very deep architectures to very compact ones. We’re excited about the promise of big data to bring big performance gains to our algorithms but also passionate about the challenge of working in data-scarce and low-power scenarios.
Furthermore, we believe that a modern computer vision system needs to be able to continuously adapt itself to its environment and to improve itself via lifelong learning. Our driving goal is to use our research to deliver embodied intelligence to our users in robotics, autonomous driving, via phone cameras and any other visual means to reach people wherever they may be.
This web site uses cookies for the site search, to display videos and for aggregate site analytics.
Learn more about these cookies in our privacy notice.
Cookie settings
You may choose which kind of cookies you allow when visiting this website. Click on "Save cookie settings" to apply your choice.
This content is currently blocked. To view the content please either 'Accept social media cookies' or 'Accept all cookies'.
For more information on cookies see our privacy notice.