EAMT 2008

12th Annual Conference of the

European Association for Machine Translation

September 22 & 23, 2008

Hamburg University (Germany)


Proceedings: papers and posters


Table of Contents


Cover and printing information


Introductions by Bente Maegaard and John Hutchins                                                                                                                                                                           1-3


Abstracts of invited talks

Nicola Cancedda: Shaping research from user requirements, and other exotic things…                                                                                                               4

Uwe Reinke: Still looking for the proper place? A view on machine translation from a translation service perspective…                                                              5


Farag Ahmed and Andreas Nürnberger: Arabic/English word translation disambiguation using parallel corpora and matching schemes                                        6-11


Dimitra Anastasiou: Identification of idioms by machine translation: a hybrid research system vs. three commercial systems                                                                    12-20


Michael Carl, Arnt Lykke Jakobsen, and Kristian T.H.Jensen: Modelling human translator behaviour with user-activity data                                                            21-26


Andreas Eisele, Christian Federmann, Hans Uszkoreit, Hervé Saint-Amand, Martin Kay, Michael Jellinghaus, Sabine Hunsicker, Teresa Herrmann, and Yu Chen: Hybrid machine translation architectures within and beyond the EuroMatrix project...                                                                                                                                              27-34


 Rauf Fatullayev, Ali Abbasov, Abulfat Fatullayev: Peculiarities of the development of the dictionary for the MT system from Azerbaijani                             35-40


Jorge González and Francisco Casacuberta: A finite-state framework for log-linear models in machine translation                                                                                    41-46


Jesús González-Rubio, Germán Sanchis-Trilles, Alfons Juan, and Francisco Casacuberta: A novel alignment model inspired on IBM Model 1                            47-56


Yvette Graham and Josef van Genabith: Packed rules for automatic transfer-rule induction                                                                                                                57-65


Ahmed Hatem and Amin Nassar: Modified Dijkstra-like search algorithm for English to Arabic machine translation system                                                                     66-71


Petr Homola and Vladislav Kuboň: Improving machine translation between closely related Romance languages                                                                                     72-77


Chen-li Kuo, and Allan Ramsay: Translating emphatic/contrastive focus from English to Mandarin Chinese...                                                                                          78-87 


Antonio L. Lagarda and Francisco Casacuberta: Applying boosting to statistical machine translation                                                                                                 88-96


Patrik Lambert and Rafael E. Banchs: Word association models and search strategies for discriminative word alignment                                                                97-103


David Mareček, Zdeněk Žabokrtský, and Václav Novák: Automatic alignment of Czech and English deep syntactic dependency trees...                                      104-113


Aurélien Max, Rafik Makhloufi, and Philippe Langlais: Explorations in using grammatical dependencies for contextual phrase translation disambiguation        114-119


Simon Mille and Leo Wanner: Multilingual summarization in practice: the case of patent claims                                                                                                          120-129


Joaquim Moré López and Salvador Climent Roca: A machine translationness typology for MT evaluations                                                                                       130-139


Rogelio Nazar, Leo Wanner, and Jorge Vivaldi: Two-step flow in bilingual lexicon extraction from unrelated corpora                                                                   140-149


Lene Offersgaard, Claus Povlsen, Lisbeth Almsten, and Bente Maegaard: Domain specific MT in use                                                                                             150-159


Daniel Ortiz-Martínez, Ismael García-Varea, and Francisco Casacuberta: Phrase-level alignment generation using a smoothed loglinear phrase-based statistical alignment model                                                                                                                                                                                                                                                                            160-169


Anders Sřgaard: Learning context-sensitive synchronous rules                                                                                                                                                              170-175


Marianne Starlander, Pierrette Bouillon, Glenn Flores, Manny Rayner, and Nikos Tsourakis: Comparing two different bidirectional versions of the limited-domain medical spoken language translator MedSLT                                                                                                                                                                                                                                          176-181


Sara Stymne and Maria Holmquist: Processing of Swedish compounds for phrase-based statistical machine translation                                                              182-191


Clare R.Voss, Matthew.Aguirre, Jeffrey Micher, Richard Chang, Jamal Laoudi, and Reginald Hobbs: Boosting performance of weak MT engines automatically: using MT output to align segments & build statistical post-editors                                                                                                                                                                                                            192-201