Christophe Mazenc

Learn More
This paper presents a study conducted in the course of implementing a project in the World Intellectual Property Organization (WIPO) on assisted translation of patent abstracts and titles from English to French. The tool (called ‘Tapta’) is trained on an extensive corpus of manually translated patents. These patents are classified, each class belonging to(More)
Described is a large-scale implementation of a Moses-based machine translation system in the United Nations aiming at accelerating the work of translators. The system (called TAPTA4UN) has been trained on extensive parallel corpora in 6 languages. Both automatic and human evaluations are provided. The system is now used in production by professional(More)
This paper presents a machine translation prototype developed with the United Nations (UN) corpus for automatic translation of UN documents from English to Spanish. The tool is based on open source Moses technology and has been developed by the World Intellectual Property Organization (WIPO). The two organizations pooled resources to create a model trained(More)
In this paper a set of de nitions describing general real number representation sys tems is presented Our purpose is to nd a su ciently wide model de nition including classical systems signed digit notation linear numeration systems p adic numbers symmetric level index arithmetic but speci c enough to make it possible to build some practical results We(More)
The purpose of this paper is to describe a modular framework for text mining that uses Canonical Text Service (CTS) as a data source. By combining standardized functionalities with standardized access to text data, this framework intends to reduce the heterogeneity of workflows in today’s Digital Humanities and act as an important element of a text research(More)
  • 1