Multilingual Dialogue-Based MT for monolingual authors: the LIDIA project and a first mockup

Boitet, Christian; Blanchon, Hervé

doi:10.1007/bf00986324

Cited by 17 publications

(9 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…one (managing the two texts with alignment services for instance), we are interested in this paper in providing services for an author who wants to obtain automatic translations of her current work. This scheme has proven to be relevant if the authoring process is augmented with an interactive disambiguation step [4,6].…”

Section: Motivationmentioning

confidence: 99%

“…In the framework of the LIDIA project [4] we investigate ways of increasing the automatic translation quality through interactive disambiguation dialogs for monolingual authors. Such an author will be able to translate her own source documents with no knowledge of the target language nor of the system itself.…”

Section: Motivationmentioning

confidence: 99%

“…First steps toward this goal [4,5] have proven the benefits of the disambiguation approach for translation, but the system was not usable because it did not cover authoring needs and imposed a linear process from edition to translation. Our current goal is to enable access to the DBMT services through a real structured document editor.…”

Section: Motivationmentioning

confidence: 99%

“…The author is requested to choose the right one [4]. Among all the available visualization techniques (graphical structures for trees, ...) we have chosen to experiment a mechanism based on structured annotations [2].…”

Section: Disambiguation Interfacementioning

confidence: 99%

See 3 more Smart Citations

Integrating translation services within a structured editor

Choumane

Blanchon²,

Roisin

2005

Proceedings of the 2005 ACM Symposium on Document Engineering

View full text Add to dashboard Cite

Section: Motivationmentioning

confidence: 99%

Section: Motivationmentioning

confidence: 99%

Section: Motivationmentioning

confidence: 99%

Section: Disambiguation Interfacementioning

confidence: 99%

See 2 more Smart Citations

Integrating translation services within a structured editor

Choumane

Blanchon²,

Roisin

2005

Proceedings of the 2005 ACM Symposium on Document Engineering

View full text Add to dashboard Cite

“…Maruyama et al [11] reported the use of the technique for Japanese, progress and elaborated in detail by Christian Boitet and Hervé Blanchon in Grenoble [11][12][13]. Since then, it has been promoted by a number of research groups in a variety of NLP systems, including 1) the LIDIA dialoguebased machine translation system by the GETA group in Grenoble; 2) the multilanguage MT system SYSTRAN; 3) the ALT-J/E system by NTT Communication Science Laboratories of Japan; 4) the UMIST MT system in Manchester, 5) a system of spoken and written translation by the Spoken Translation group in the USA, 6) a system of multilingual search and Internet navigation by DFKI and the University of Saarland in Germany, and many others.…”

Section: Interactive Disambiguation: a Promising Solutionmentioning

confidence: 99%

Interactive Resolution of Intrinsic and Translational Ambiguity in a Machine Translation System

Boguslavsky

Iomdin

Lazursky

et al. 2005

Computational Linguistics and Intelligent Text Processing

View full text Add to dashboard Cite

Abstract. The paper presents the module of interactive word sense disambiguation and syntactic ambiguity resolution used within a machine translation system, ETAP-3. The method applied consists in asking the user to identify a word sense, or a syntactic interpretation, whenever the system lacks reliable data to make the choice automatically. In lexical disambiguation, part of man-machine dialogue refers to the analysis phase, while the other part is activated during transfer. For this purpose, entries of the working dictionaries of the system are supplemented with clear diagnostic comments and illustrations that enable the user to choose the most appropriate option and in this way channel the course of system operation. Introductory Remarks. ETAP-3 OverviewETAP-3 is a full-scale rule-based machine translation system that serves RussianEnglish and English-Russian pairs and has a number of small prototype modules for Russian-German, French-Russian, Russian-Korean, Russian-Spanish and ArabicEnglish translation. The MT system is developed as part of a multipurpose linguistic processor at the Laboratory of computational linguistics, Institute for Information Transmission Problems in Moscow [1][2][3][4]. Other modules of the processor include a parsing tool for deep syntactic tagging of text corpora, a UNL enconverter and deconverter tool, and several smaller-scale components (a module of synonymous paraphrasing of sentences, syntax checker, and a computer-assisted language learning tool).

show abstract

Machine Translation

Boitet

2006

Encyclopedia of Cognitive Science

View full text Add to dashboard Cite

show abstract

Multilingual Dialogue-Based MT for monolingual authors: the LIDIA project and a first mockup

Cited by 17 publications

References 23 publications

Integrating translation services within a structured editor

Integrating translation services within a structured editor

Interactive Resolution of Intrinsic and Translational Ambiguity in a Machine Translation System

Machine Translation

Contact Info

Product

Resources

About