newLCSTAR_logo3.gif (16414 bytes)            Public Documents

                    The project is now over, this web page will be maintained until February 2006

 

Home
Project Overview
Consortium
Public Documents
Related Sites
Internal Pages

 

    PR-material

    BD10267_.GIF (311 bytes) LC-STAR Leaflet (yellow)

         LC-STAR Leaflet (blue)

 

WB00941_.GIF (1211 bytes)

    Public Deliverables

    BD10267_.GIF (311 bytes) Project Management

        D0.3.1 Annual Public Report

        D0.3.2 Annual Public Report

        D0.3.3 Annual Public Report

        D0.2.6 Final Report

 

    BD10267_.GIF (311 bytes) Technical Work

        D1.1 Specification of corpora and word lists in 12 languages

        D2.1 Language-independent specification of contents of lexica

        D2.2 Report on properties of each language relevant for determining effort

        D2.3 Definition of representation format

        D2.4 Language-dependent specification of the contents of the lexicon for each language

        D4.1 Overview on speech centered translation

        D4.2 Description of LR used for experiments

        D4.4 First experimental results on baseline for speech-to-speech translation systems

        D4.5 Results on different structured LR for speech-to-speech translation systems

        D5.5 Language independent specification of LR for translation

        D5.6 Language specific specification of LR for translation

        D6.1 Specification of validation criteria for lexica for recognition and synthesis

        D6.3 Specification of validation criteria for LR for speech centered translation

        D7.2 Acceptance testing of the demonstrator

        DTD for the large lexica

 

        Back to Top

 

WB00941_.GIF (1211 bytes)

      Other publications related to the project

 

        Author(s):                                   Title:

N. Ueffing, H. Ney

 

 

Training Corpus Size and Statistical Machine Translation Quality

Informatiktage 2002 of the Gesellschaft für Informatik e.V., Bad Schussenried, Germany, November 2002.

N. Ueffing, H. Ney

 

 

Using POS Information for Statistical Machine Translation into Morphologically Rich Languages

EACL2003, Budapest, Hungary, April 2003.

E. Hartikainen, G. Maltese, A. Moreno, S. Shammass, U. Ziegenhain Large lexica for Speech-to-Speech Translation: From Specification to Creation

Poster

Eurospeech 2003, Geneva, Switzerland, September 2003.

D. Conejero, J. Giménez, V. Arranz, A. Bonafonte, N. Pascual, N. Castell, A. Moreno Lexica and Corpora for Speech-to-Speech Translation: A Trilingual Approach

Eurospeech 2003, Geneva, Switzerland, September 2003.

A. Moreno Project presentation

SEPLN2003, Madrid, Spain, September 2003.

G. Leusch, N. Ueffing, H. Ney A Novel String-to-String Distance Measure With Applications to Machine Translation Evaluation

MT Summit IX, New Orleans, LA, September 2003. Proceedings p. 240-247.

N. Ueffing, K. Macherey, H. Ney Confidence Measures for Statistical Machine Translation

MT Summit IX, New Orleans, LA, September 2003. Proceedings p. 394-401.

V. Arranz, N. Castell, J. Giménez Development of Languge Resources for Speech-to-Speech Translation

Poster

RANLP2003, Borovets, Bulgaria, September 2003.

H. Fersøe, E. Hartikainen, H. van den Heuvel, G. Maltese, A. Moreno, S. Shammass, U. Ziegenhain Creation and Validation of Large Lexica for Speech-to-Speech Translation Purposes

Poster

LREC2004, Lisbon, Portugal, May 2004.

M. Popovic, H. Ney Towards the Use of Word Stems and Suffixes for Statistical Machine Translation

LREC2004, Lisbon, Portugal, May 2004.

D. Verdonik, M. Rojc, Z. Kacic Creating Slovenian Language Resources for Development of Speech-to-Speech Translation Components

LREC2004, Lisbon, Portugal, May 2004.

V. Arranz, N. Castell, J.M. Crego, J. Giménez, A. de Gispert, P. Lambert Bilingual Connections for Trilingual Corpora: An XML Approach

Poster

LREC2004, Lisbon, Portugal, May 2004.

U. Ziegenhain, A. Moreno, N. Castell Creation of lexica for statistical based speech-to-speech translation

AST 2004, Maribor, Slovenia, July 2004.

D. Verdonik Slovenian lexica and corpora within the LC-STAR project

AST 2004, Maribor, Slovenia, July 2004.

R. Zens, E. Matusov, H. Ney Improved Word Alignment Using a Symmetric Lexicon Model

Coling2004, Geneva, Switzerland, August 2004.

M. Popovic, H. Ney Improving Word Alignment Quality Using Morpho-Syntactic Information

Coling2004, Geneva, Switzerland, August 2004.

F. de Vriend, N. Castell, J. Giménez, G. Maltese LC-STAR: XML-coded Phonetic Lexica and Bilingual Corpora for Speech-to-Speech Translation

Papillon2004, Workshop on Multilingual Lexical Databases, Grenoble, France, August 2004.

E. Matusov, M. Popovic, R. Zens, H. Ney  

Statistical Machine Translation of Spontaneous Speech with Scarce Resources

IWSLT, Kyoto, Japan, September/October 2004.

O. Bender, R. Zens, E. Matusov, H. Ney  

Alignment Templates: The RWTH SMT System

IWSLT, Kyoto, Japan, September/October 2004.

D. Verdonik, M. Rojc Jezikovni viri projekta LC-STAR

JT04 (Fourth Language Technologies Conference), Ljubljana, Slovenia, October 2004.

F. de Vriend, G. Maltese Exploring XML-based Technologies and Procedures for Quality Evaluation from a Real-Life Case Perspective

Poster

INTERSPEECH 2004 - ICSLP, Korea, October 2004.

V. Arranz, N. Castell, J. Giménez Creación de Recursos Lingüísticos para la Traducción Automática

Slides (in English)

III Jordanas en Tecnología del Habla, Valencia, Spain, November 2004.

V. Arranz, N. Castell, J. Giménez Creació de recursos lingüístics per a la traducció automàtica

CELC´04 (2nd Conference on Engineering in Catalan Language), Andorra, November 2004.

 

        Back to Top

    

    WB00941_.GIF (1211 bytes)
    Last updated: May 11, 2005 by Elviira Hartikainen.