WMT07

Workshop on Machine Translation


The Second Workshop on Machine Translation (WMT07) took place on 23 June, 2007, in Prague, Czech Republic. It was organised by WMT.

statmt.org/wmt07/program.html

Table of contents
  1. Tasks
  2. Schedule
  3. Results
    1. Translation
      1. → English
      2. English →

Tasks

Schedule

   
08:30 – 08:35 Opening Remarks
08:35 – 08:55 Full Paper Session 1
Using Dependency Order Templates to Improve Generality in Translation
Arul Menezes, Chris Quirk
08:55 – 09:15 CCG Supertags in Factored Statistical Machine Translation
Alexandra Birch, Miles Osborne, Philipp Koehn
09:15 – 09:35 Integration of an Arabic Transliteration Module into a Statistical Machine Translation System
Mehdi M. Kashani, Eric Joanis, Roland Kuhn, George Foster, Fred Popowich
09:35 – 09:55 Exploring Different Representational Units in English-to-Turkish Statistical Machine Translation
Kemal Oflazer, Ilknur Durgar El-Kahlout
09:55 – 10:15 Can We Translate Letters?
David Vilar, Jan-Thorsten Peter, Hermann Ney
10:15 – 10:45 Poster Session for Full Papers
Boaster Session
10:45 – 11:45 Full Paper Poster Session
☕️
  Context-aware Discriminative Phrase Selection for Statistical Machine Translation
Jesús Giménez, Lluís Màrquez
  A Dependency Treelet String Correspondence Model for Statistical Machine Translation
Deyi Xiong, Qun Liu, Shouxun Lin
  Word Error Rates: Decomposition over POS classes and Applications for Error Analysis
Maja Popovic, Hermann Ney
  Speech-Input Multi-Target Machine Translation
Alicia Pérez, M. Teresa González, M. Inés Torres, Francisco Casacuberta
  Meta-Structure Transformation Model for Statistical Machine Translation
Jiadong Sun, Tiejun Zhao, Huashen Liang
  Training Non-Parametric Features for Statistical Machine Translation
Patrick Nguyen, Milind Mahajan, Xiaodong He
  Using Word-Dependent Transition Models in HMM-Based Word Alignment for Statistical Machine Translation
Xiaodong He
  Efficient Handling of N-gram Language Models for Statistical Machine Translation
Marcello Federico, Mauro Cettolo
  Human Evaluation of Machine Translation Through Binary System Comparisons
David Vilar, Gregor Leusch, Hermann Ney, Rafael E. Banchs
  Labelled Dependencies in Machine Translation Evaluation
Karolina Owczarzak, Josef van Genabith, Andy Way
11:45 – 12:30 Invited Talk
Jean Senellart, Systran
12:30 - 14:00 🍴
14:00 – 14:20 Full Paper Session 2
An Iteratively-Trained Segmentation-Free Phrase Translation Model for Statistical Machine Translation
Robert Moore, Chris Quirk
14:20 – 14:40 Using Paraphrases for Parameter Tuning in Statistical Machine Translation
Nitin Madnani, Necip Fazil Ayan, Philip Resnik, Bonnie Dorr
14:40 – 15:00 Mixture-Model Adaptation for SMT
George Foster, Roland Kuhn
15:00 – 15:15 Shared Task
(Meta-) Evaluation of Machine Translation
Chris Callison-Burch, Cameron Fordyce, Philipp Koehn, Christof Monz, Josh Schroeder
15:15 – 15:45 Boaster Session for Shared Task Posters
15:45 – 16:45 Shared Task Poster Session
☕️
  Ngram-Based Statistical Machine Translation Enhanced with Multiple Weighted Reordering Hypotheses
Marta R. Costa-jussià, Josep M. Crego, Patrik Lambert, Maxim Khalilov, José A. R. Fonollosa, José B. Mariño, Rafael E. Banchs
  Analysis of Statistical and Morphological Classes to Generate Weigthed Reordering Hypotheses on a Statistical Machine Translation System
Marta R. Costa-jussià, José A. R. Fonollosa
  Domain Adaptation in Statistical Machine Translation with Mixture Modelling
Jorge Civera, Alfons Juan
  Getting to Know Moses: Initial Experiments on German-English Factored Translation
Maria Holmqvist, Sara Stymne, Lars Ahrenberg
  NRC’s PORTAGE System for WMT 2007
Nicola Ueffing, Michel Simard, Samuel Larkin, Howard Johnson
  Building a Statistical Machine Translation System for French Using the Europarl Corpus
Holger Schwenk
  Multi-Engine Machine Translation with an Open-Source SMT Decoder
Yu Chen, Andreas Eisele, Christian Federmann, Eva Hasler, Michael Jellinghaus, Silke Theison
  The ISL Phrase-Based MT System for the 2007 ACL Workshop on Statistical Machine Translation
Matthias Paulik, Kay Rottmann, Jan Niehues, Silja Hildebrand, Stephan Vogel
  Rule-Based Translation with Statistical Phrase-Based Post-Editing
Michel Simard, Nicola Ueffing, Pierre Isabelle, Roland Kuhn
  The “Noisier Channel”: Translation from Morphologically Complex Languages
Christopher J. Dyer
  UCB System Description for the WMT 2007 Shared Task
Preslav Nakov, Marti Hearst
  The Syntax Augmented MT (SAMT) System at the Shared Task for the 2007 ACL Workshop on Statistical Machine Translation
Andreas Zollmann, Ashish Venugopal, Matthias Paulik, Stephan Vogel
  Statistical Post-Editing on SYSTRAN’s Rule-Based Translation System
Loïc Dugast, Jean Senellart, Philipp Koehn
  Experiments in Domain Adaptation for Statistical Machine Translation
Philipp Koehn, Josh Schroeder
  METEOR: An Automatic Metric for MT Evaluation with High Levels of Correlation with Human Judgments
Alon Lavie, Abhaya Agarwal
16:45 – 17:05 Full Paper Session 4
English-to-Czech Factored Machine Translation
Ondrej Bojar
17:05 – 17:25 Sentence Level Machine Translation Evaluation as a Ranking
Yang Ye, Ming Zhou, Chin-Yew Lin
17:25 – 17:45 Localization of Difficult-to-Translate Phrases
Behrang Mohit, Rebecca Hwa
17:45 – 18:05 Linguistic Features for Automatic Evaluation of Heterogenous MT Systems
Jesús Giménez, Lluís Màrquez

Results

Full results of the shared task: (Meta-) Evaluation of Machine Translation

Translation

The results were determined with a relative ranking, the > others (“greater than others”) score, an adequacy and fluency judgement, and a constituent ranking.

The automatic evaluation results were excluded from the article as the findings conclude the human judgments to be authoritative.

→ English

Language pair System > others Adequacy Fluency Constituent
Czech News → UMD 0.627 0.550 0.592 -
French Europarl → LIMSI
UEDIN
-
0.514
0.634
-
-
0.635
0.290
-
French News → LIMSI
UPC
0.494
-
-
0.576
0.596
-
0.312
-
German Europarl → SYSTRAN 0.530 0.562 0.594 0.302
German News → SYSTRAN 0.563 0.552 0.560 0.344
Spanish Europarl → UEDIN
UPC
-
0.500
0.593
-
0.610
-
-
0.188
Spanish News → UPC 0.537 0.566 0.543 0.312

English →

Language pair System > others Adequacy Fluency Constituent
→ Czech News PCT
CU
0.499
-
0.542
-
0.541
-
-
0.440
→ French Europarl SYSTRAN-NRC
LIMSI
UEDIN
0.512
-
-
-
0.635
-
-
0.627
-
-
-
0.273
→ French News SYSTRAN
SYSTRAN-NRC
0.634
-
-
0.557
-
0.572
0.440
-
→ German Europarl SYSTRAN
UEDIN
0.511
-
-
0.569
-
0.576
-
0.350
→ German News SYSTRAN 0.582 0.542 0.556 0.351
→ Spanish Europarl UEDIN
UPV
0.468
-
0.586
-
0.638
-
-
0.246
→ Spanish News SYSTRAN
UPC
0.481
-
-
0.510
0.507
-
0.352
-

Want to learn more about WMT07?


Edit this article →

Machine Translate is created and edited by contributors like you!

Learn more about contributing →

Licensed under CC-BY-SA-4.0.

Cite this article →