5th EAMT Workshop

"Harvesting existing resources"

11-12 May 2000

Lubljana, Slovenia

Organized by the European Association for Machine Translation

in cooperation with the Slovenian Language Technologies Society.



Table of Contents

Introduction -- John Hutchins [PDF, 25KB]

Translation Memories

Extending Translation Memories -- Emmanuel Planas [PDF, 170KB]

Extracting Terms and Terminological Collocations from the ELAN Slovene-English Parallel Corpus -- Špela Vintar [PDF, 132KB]

Extracting Textual Associations in Part-of-Speech Tagged Corpora -- Gaël Dias, Sylvie Guilloré, José Gabriel Pereira Lopes [PDF, 99KB]

MT and Language Resources

Statistical Machine Translation -- Franz Josef Och, Hermann Ney [PDF, 214KB]

POLENG - Adjusting a Rule-Based Polish-English Machine Translation System by Means of Corpus Analysis -- Krzysztof Jassem, Filip Graliński, Grzegorz Krynicki [PDF, 143KB]

Slovene-English Datasets for MT -- Tomaž Erjavec [PDF, 104KB]

Evaluation of MT Systems

The IAMT Certification Initiative and Defining Translation System Categories -- John Hutchins [PDF, 72KB]

Evaluation as a Language Technology Deployment Trigger -- Rita Nübel, Jörg Schütz [PDF, 55KB]

Translating EU Documentation

Language Technology in EU Institutions -- Dimitri Theologitis [not available]

Translation of EU Legislation in Slovenia -- Adriana Krstič [PDF, 21KB]

Experience of MT within a Productive Translation Workflow

MT within a Productive Translation Workflow -- Anthony Clarke [PDF, 195KB]

Computer Assisted Business Process Management in Translation and Localisation Companies -- Adriane Rinsche [PDF, 109KB]


[Conference reports in MT News International no. 25, Summer 2000]