Link Search Menu Expand Document

WMT12

Workshop on Machine Translation


The Seventh Workshop on Machine Translation (WMT12) took place from 7 June to 8 June, 2012, in Montreal, Quebec.

statmt.org/wmt12/program.html

Table of contents
  1. Tasks
  2. Schedule
    1. Day 1
    2. Day 2
  3. Results
    1. News translation
      1. → English
      2. English →

Tasks

Schedule

Day 1

   
09:00 – 09:10 Opening Remarks: Future Funding and Research Survey Wiki
09:10 – 09:30 Session 1: Shared Tasks and their Evaluation
Putting Human Assessments of Machine Translation Systems in Order
Adam Lopez
09:30 – 10:30 Findings of the 2012 Workshop on Statistical Machine Translation
Chris Callison-Burch, Philipp Koehn, Christof Monz, Matt Post, Radu Soricut, Lucia Specia
10:30 – 11:00 ☕️
11:00 – 12:40 Session 2: Shared Quality Estimation and Metrics Tasks
Poster Session: Evaluation Metrics
  Semantic Textual Similarity for MT evaluation
Julio Castillo, Paula Estrella
  Improving AMBER, an MT Evaluation Metric
Boxing Chen, Roland Kuhn, George Foster
  TerrorCat: a Translation Error Categorization-based MT Quality Metric
Mark Fishel, Rico Sennrich, Maja Popović, Ondrej Bojar
  Class error rates for evaluation of machine translation output
Maja Popovic
  SPEDE: Probabilistic Edit Distance Metrics for MT Evaluation
Mengqiu Wang, Christopher Manning
11:00 – 12:40 Poster Session: Quality Estimation Task
  Quality estimation for Machine Translation output using linguistic analysis and decoding features
Eleftherios Avramidis
  Black Box Features for the WMT 2012 Quality Estimation Shared Task
Christian Buck
  Linguistic Features for Quality Estimation
Mariano Felice, Lucia Specia
  PRHLT Submission to the WMT12 Quality Estimation Task
Jesús González-Rubio, Alberto Sanchís, Francisco Casacuberta
  Tree Kernels for Machine Translation Quality Estimation
Christian Hardmeier, Joakim Nivre, Jörg Tiedemann
  LORIA System for the WMT12 Quality Estimation Shared Task
David Langlois, Sylvain Raybaud, Kamel Smaïli
  Quality Estimation: an experimental study using unsupervised similarity measures
Erwan Moreau, Carl Vogel
  The UPC Submission to the WMT 2012 Shared Task on Quality Estimation
Daniele Pighin, Meritxell González, Lluís Màrquez
  Morpheme- and POS-based IBM1 and language model scores for translation quality estimation
Maja Popovic
  DCU-Symantec Submission for the WMT 2012 Quality Estimation Task
Raphael Rubino, Jennifer Foster, Joachim Wagner, Johann Roturier, Rasul Samad Zadeh Kaljahi, Fred Hollowood
  The SDL Language Weaver Systems in the WMT12 Quality Estimation Shared Task
Radu Soricut, Nguyen Bach, Ziyuan Wang
  Regression with Phrase Indicators for Estimating MT Quality
Chunyang Wu, Hai Zhao
12:40 – 14:00 🍴
14:00 – 15:30 Session 3: Invited Talk
Deployment of SMT for the IBM Enterprise
Salim Roukos
15:30 – 16:00 ☕️
16:00 – 16:20 Session 4: Confidence Estimation and System Combination
Non-Linear Models for Confidence Estimation
Yong Zhuang, Guillaume Wisniewski, François Yvon
16:20 – 16:40 Combining Quality Prediction and System Selection for Improved Automatic Translation Output
Radu Soricut, Sushant Narsale
16:40 – 17:00 Match without a Referee: Evaluating MT Adequacy without Reference Translations
Yashar Mehdad, Matteo Negri, Marcello Federico
17:00 – 17:20 Comparing human perceptions of post-editing effort with post-editing operations
Maarit Koponen
17:20 – 17:40 Review of Hypothesis Alignment Algorithms for MT System Combination via Confusion Network Decoding
Antti-Veikko Rosti, Xiaodong He, Damianos Karakos, Gregor Leusch, Yuan Cao, Markus Freitag, Spyros Matsoukas, Hermann Ney, Jason Smith, Bing Zhang

Day 2

   
09:00 – 09:20 Session 5: Reordering, Syntax and Semantics
On Hierarchical Re-ordering and Permutation Parsing for Phrase-based Decoding
Colin Cherry, Robert C. Moore, Chris Quirk
09:20 – 09:40 CCG Syntactic Reordering Models for Phrase-based Machine Translation
Dennis Nolan Mehay, Christopher Hardie Brew
09:40 – 10:00 Using Categorial Grammar to Label Translation Rules
Jonathan Weese, Chris Callison-Burch, Adam Lopez
10:00 – 10:20 Using Syntactic Head Information in Hierarchical Phrase-Based Translation
Junhui Li, Zhaopeng Tu, Guodong Zhou, Josef van Genabith
10:20 – 10:40 Fully Automatic Semantic MT Evaluation
Chi-kiu Lo, Anand Karthik Tumuluru, Dekai Wu
10:40 – 11:00 ☕️
11:00 – 12:40 Session 6: Translation Task
Poster Session: Translation Task
  Probes in a Taxonomy of Factored Phrase-Based Models
Ondrej Bojar, Bushra Jawaid, Amir Kamran
  The CMU-Avenue French-English Translation System
Michael Denkowski, Greg Hanneman, Alon Lavie
  Formemes in English-Czech Deep Syntactic MT
Ondrej Dušek, Zdenek Žabokrtský, Martin Popel, Martin Majliš, Michal Novák, David Mareček
  The TALP-UPC phrase-based translation systems for WMT12: Morphology simplification and domain adaptation
Lluis Formiga, Carlos A. Henríquez Q., Adolfo Hernández, José B. Mariño, Enric Monte, José A. R. Fonollosa
  Joshua 4.0: Packing, PRO, and Paraphrases
Juri Ganitkevitch, Yuan Cao, Jonathan Weese, Matt Post, Chris Callison-Burch
  Syntax-aware Phrase-based Statistical Machine Translation: System Description
Ulrich Germann
  QCRI at WMT12: Experiments in Spanish-English and German-English Machine Translation of News Text
Francisco Guzman, Preslav Nakov, Ahmed Thabet, Stephan Vogel
  The RWTH Aachen Machine Translation System for WMT 2012
Matthias Huck, Stephan Peitz, Markus Freitag, Malte Nuhn, Hermann Ney
  Machine Learning for Hybrid Machine Translation
Sabine Hunsicker, Chen Yu, Christian Federmann
  Towards Effective Use of Training Data in Statistical Machine Translation
Philipp Koehn, Barry Haddow
  Joint WMT 2012 Submission of the QUAERO Project
Freitag Markus, Peitz Stephan, Huck Matthias, Ney Hermann, Niehues Jan, Herrmann Teresa, Waibel Alex, Hai-son Le, Lavergne Thomas, Allauzen Alexandre, Buschbeck Bianka, Crego Joseph Maria, Senellart Jean
  LIMSI @ WMT12
Hai-Son Le, Thomas Lavergne, Alexandre Allauzen, Marianna Apidianaki, Li Gong, Aurélien Max, Artem Sokolov, Guillaume Wisniewski, François Yvon
  UPM system for WMT 2012
Verónica López-Ludeña, Rubén San-Segundo, Juan M. Montero
  PROMT DeepHybrid system for WMT12 shared translation task
Alexander Molchanov
  The Karlsruhe Institute of Technology Translation Systems for the WMT 2012
Jan Niehues, Yuqi Zhang, Mohammed Mediani, Teresa Herrmann, Eunah Cho, Alex Waibel
  Kriya - The SFU System for Translation Task at WMT-12
Majid Razmara, Baskaran Sankaran, Ann Clifton, Anoop Sarkar
  DEPFIX: A System for Automatic Correction of Czech MT Outputs
Rudolf Rosa, David Mareček, OndÅ™ej Dušek
  LIUM’s SMT Machine Translation Systems for WMT 2012
Christophe Servan, Patrik Lambert, Anthony Rousseau, Holger Schwenk, Loïc Barrault
  Selecting Data for English-to-Czech Machine Translation
Aleš Tamchyna, Petra Galuščáková, Amir Kamran, Miloš Stanojević, Ondrej Bojar
  DFKI’s SMT System for WMT 2012
David Vilar
  GHKM Rule Extraction and Scope-3 Parsing in Moses
Philip Williams, Philipp Koehn
  Data Issues of the Multilingual Translation Matrix
Daniel Zeman
12:40 – 14:00 🍴
14:00 – 14:20 Session 7: Corpus Creation and Adaptation
Constructing Parallel Corpora for Six Indian Languages via Crowdsourcing
Matt Post, Chris Callison-Burch, Miles Osborne
14:20 – 14:40 Twitter Translation using Translation-Based Cross-Lingual Retrieval
Laura Jehl, Felix Hieber, Stefan Riezler
14:40 – 15:00 Analysing the Effect of Out-of-Domain Data on SMT Systems
Barry Haddow, Philipp Koehn
15:00 – 15:20 Evaluating the Learning Curve of Domain Adaptive Statistical Machine Translation Systems
Nicola Bertoldi, Mauro Cettolo, Marcello Federico, Christian Buck
15:20 – 15:40 The Trouble with SMT Consistency
Marine Carpuat, Michel Simard
15:40 – 16:00 ☕️
16:00 – 16:20 Session 8: Phrase Model Training and Optimization
Phrase Model Training for Statistical Machine Translation with Word Lattices of Preprocessing Alternatives
Joern Wuebker, Hermann Ney
16:20 – 16:40 Leave-One-Out Phrase Model Training for Large-Scale Deployment
Joern Wuebker, Mei-Yuh Hwang, Chris Quirk
16:40 – 17:00 Direct Error Rate Minimization for Statistical Machine Translation
Tagyoung Chung, Michel Galley
17:00 – 17:20 Optimization Strategies for Online Large-Margin Learning in Machine Translation
Vladimir Eidelman

Results

Full results of the shared tasks: Findings of the 2012 Workshop on Statistical Machine Translation

News translation

The results were determined with a relative ranking, the > others (“greater than others”) score.

It measures how often a system was judged to be better than any other system.

→ English

Language pair System > others
Czech → ONLINE-B
UEDIN
0.65
0.60
Spanish → ONLINE-A
ONLINE-B
QCRI
UEDIN
0.62
0.61
0.60
0.58
French → LIMSI
KIT
ONLINE-A
CMU
ONLINE-B
0.63
0.61
0.59
0.57
0.57
German → ONLINE-A
ONLINE-B
UEDIN
RWTH
KIT
0.65
0.65
0.60
0.56
0.55

English →

Language pair System > others
→ Czech CU-DEPFIX
UEDIN
CU-BOJAR
CU-TECTOMT
0.66
0.56
0.54
0.53
→ Spanish ONLINE-B
ONLINE-A
UPC
UEDIN
0.65
0.56
0.52
0.52
→ French LIMSI
KIT
0.66
0.59
→ German ONLINE-B
RBMT-4
LIMSI
UEDIN-WILLIAMS
KIT
UEDIN
RWTH
0.64
0.58
0.55
0.51
0.50
0.47
0.47

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 →