• Corpus ID: 20961931

La coédition langue UNL pour partager la révision entre langues d'un document multilingue. (Coedition Language UNL to share the postedition among languages in a multilingual document)

  title={La co{\'e}dition langue UNL pour partager la r{\'e}vision entre langues d'un document multilingue. (Coedition Language UNL to share the postedition among languages in a multilingual document)},
  author={Wang-Ju Tsai},
La coedition d'un texte en langue naturelle et de sa representation dans une forme interlingue semble le seul moyen de partager la revision du texte vers plusieurs langues. Pour diverses raisons, les graphes UNL sont les meilleurs candidats dans ce contexte. Nous developpons un prototype ou, dans le scenario avec partage le plus simple, des utilisateurs "naifs" interagissent directement avec le texte dans leur langue (L0), et indirectement avec le graphe associe. Le graphe modifie est ensuite… 
Multilinguïsation des systèmes de e-commerce traitant des énoncés spontanés en langue naturelle. (Multilinguïsation of e-commerce system treating spontaneous utterances in natural language)
La multilinguisation, ou « portage linguistique » (plus simple que the localisation) des services de gestion de contenu traitant des enonces spontanes en langue naturelle, souvent bruites, mais contraints par the situation, and constituant toujours un « sous-langage » plus ou moins restreint.
Graphes linguistiques multiniveau pour l'extraction de connaissances : l'exemple des collocations. (Multilevel linguistic graphs for knowledge extraction : the example of collocations)
Pour modeliser au mieux les phenomenes linguistiques dans les systemes de traitement automatique des langues (traduction, analyse, etc.), il faut disposer de ressources de qualite sont souvent incompletes and ne permettent pas of traiter correctement les donnees.
Aides informatisées à la traduction collaborative bénévole sur le Web. (Computer-Aided Translation Environment for Volunteer Translation)
  • Youcef Bey
  • Computer Science, Political Science
  • 2008
La croissance remarquable de la quantite des documents multilingues dissemines en ligne gratuitement est le resultat d'un travail laborieux de communautes benevoles qui sont malheureusement technologiquement marginalisees, et privees de toute aide « linguistique » a la traduction.
A Web-oriented System to Manage the Translation of an Online Encyclopedia
A Web-oriented system for evaluating, presenting, processing, enlarging and annotating corpora of translations, previously applied to a real MT evaluation task, by applying contributive on-line human post-edition to results of machine translation systems and of UNL deconverters is described.
Gradable Quality Translations through Mutualization of Human Translation and Revision, and UNL-Based MT and Coedition
An organization where this can be obtained through a combination of "mutualized" human work and automatic NLP techniques, using the UNL language of "anglosemantic" graphs as a "pivot".
Extending an on-line parallel corpus management system to handle specific types of structured documents
SECTra_w is described, a web-oriented system which has been used for online MT evaluations, and has recently been extended to handle multimodal documents such as French-Chinese/Vietnamese/Hindi/Tamil interpreted bilingual spontaneous dialogues and multilingual written articles of an online encyclopedia annotated with UNL graphs.
Message Automata for Messages with Variants, and Methods for Their Translation
Controlled loop-free FSAs, called here “message automata” (MAs), are proposed to model such messages with variables and variants, and a still speculative idea is to use a UNL graph conform to the official specifications, but with some special conventions, to represent a message with variables, and generate the language-specific MAs from it.
About and Around the French Enconverter and the French Deconverter
A few general points concerning the possibility of designing dependency trees equivalent to UNL graphs, the treatment of the ambiguity and anaphora resolution, and the structure of the compound nodes are discussed.


Un essai de réponse à quelques questions théoriques et pratiques liées à la traduction automatique : définition d'un système prototype
HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not, for teaching and research institutions in France or abroad, or from public or private research centers.
On UNL as the future “html of the linguistic content” & the reuse of existing NLP components in UNL-related applications with the example of a UNL-French deconverter
An UNL-French deconverter organized as a specific "localizer" followed by a classical MT transfer and an existing generator is described, leading as well to the reuse of existing NLP components as to the development of original tools in a variety of possible applications.
Coedition to Share Text Revision across Languages and Improve MT a Posteriori
A central goal of this research is to merge approaches from pivot MT, interactive MT, and multilingual text authoring with the best candidates in this context, UNL graphs.
A "Pivot" XML-Based Architecture for Multilingual, Multiversion Documents: Parallel Monolingual Documents Aligned Through a Central Correspondence Descriptor and Possible Use of UNL
This work is developing a Java application to enable direct editing of a multilingual document through the web, at the level of monolingual volumes as well as through bilingual or trilingual interfaces inspired by those of commercial "translation workbenches".
Multilingual documents management by using Universal Networking Language UNL on Alignment Gestion Tool OGA
The paper aims to present multilingual document alignment and translation on the platform OGA by using the UNL (Universal Networking Language), a sort of interlingua such as pivot languages in certain MT systems, which enables to translate documents into several different languages.
Multilingual Dialogue-Based MT for monolingual authors: the LIDIA project and a first mockup
The main situational, linguistic and ergonomic issues in DBMT for monolingual authors are described and ongoing work on the LIDIA project is described, which is the production of multilingual technical documentation in the form of HyperCard stacks.
UNL Document Summarization
A summarization method to UNL document summarization that directly process the UNL semantic information to extract the essence of the document to improve the summarization quality.
Structural and Lexical Transfer : From an UNL graph to an Equivalent NL Dependency
Multi-lingual generation starts from non-linguistic content representations for generating texts in different languages that are equivalent in meaning. In contrast, cross-lingual generation is based
An interlingua based on domain actions for machine translation of task-oriented dialogues
An interlingua for spoken language translation that is based on domain actions in the travel planning domain, used by the C-STAR speech translation consortium for translating travel planning dialogues in six languages: English, Japanese, German, Korean, Italian, and French is described.
Document structure and multilingual authoring
The IG (Interaction Grammar) formalism is described, an extension of DTD's which permits powerful linguistic manipulations, and its application to the production of multilingual versions of a certain class of pharmaceutical documents is shown.