Workshop Program

EMNLP 2011 SIXTH WORKSHOP
ON STATISTICAL MACHINE TRANSLATION

July 30-31, 2011
Edinburgh, UK

Saturday, July 30, 2011

Session 1: Shared Tasks and Evaluation (Chair: Chris Callison-Burch)

9:00–9:25 A Grain of Salt for the WMT Manual Evaluation
Ondrej Bojar, Miloš Ercegovčević, Martin Popel and Omar Zaidan

9:25–9:50 A Lightweight Evaluation Framework for Machine Translation Reordering
David Talbot, Hideto Kazawa, Hiroshi Ichikawa, Jason Katz-Brown, Masakazu Seno and Franz Och

9:50–10:30 Findings of the 2011 Workshop on Statistical Machine Translation
Chris Callison-Burch, Philipp Koehn, Christof Monz and Omar Zaidan

10:30–11:00 Coffee

Session 2: Shared Metrics and System Combination Tasks

11:00–12:40 Poster Session Metrics

Evaluate with Confidence Estimation: Machine ranking of translation outputs using grammatical features
Eleftherios Avramidis, Maja Popović, David Vilar and Aljoscha Burchardt

AMBER: A Modified BLEU, Enhanced Ranking Metric
Boxing Chen and Roland Kuhn

TESLA at WMT 2011: Translation Evaluation and Tunable Metric
Daniel Dahlmeier, Chang Liu and Hwee Tou Ng

Meteor 1.3: Automatic Metric for Reliable Optimization and Evaluation of Machine Translation Systems
Michael Denkowski and Alon Lavie

Approximating a Deep-Syntactic Metric for MT Evaluation and Tuning
Matouš Macháček and Ondrej Bojar

Evaluation without references: IBM1 scores as evaluation metrics
Maja Popović, David Vilar, Eleftherios Avramidis and Aljoscha Burchardt

Morphemes and POS tags for n-gram based evaluation metrics
Maja Popović

E-rating Machine Translation
Kristen Parton, Joel Tetreault, Nitin Madnani and Martin Chodorow

TINE: A Metric to Assess MT Adequacy
Miguel Rios, Wilker Aziz and Lucia Specia

Regression and Ranking based Optimisation for Sentence Level MT Evaluation
Xingyi Song and Trevor Cohn

MAISE: A Flexible, Configurable, Extensible Open Source Package for Mass AI System Evaluation
Omar Zaidan

11:00–12:40 Poster Session System Combination

MANY improvements for WMT11
Loïc Barrault

The UPV-PRHLT combination system for WMT 2011
Jesús González-Rubio and Francisco Casacuberta

CMU System Combination in WMT 2011
Kenneth Heafield and Alon Lavie

The RWTH System Combination System for WMT 2011
Gregor Leusch, Markus Freitag and Hermann Ney

Expected BLEU Training for Graphs: BBN System Description for WMT11 System Combination Task
Antti-Veikko Rosti, Bing Zhang, Spyros Matsoukas and Richard Schwartz

The UZH System Combination System for WMT 2011
Rico Sennrich

Description of the JHU System Combination Scheme for WMT 2011
Daguang Xu, Yuan Cao and Damianos Karakos

12:40–14:00 Lunch

Session 3: Language Models and Document Alignment (Chair: David Talbot)

14:00–14:25 Multiple-stream Language Models for Statistical Machine Translation
Abby Levenberg, Miles Osborne and David Matthews

14:25–14:50 KenLM: Faster and Smaller Language Model Queries
Kenneth Heafield

14:50–15:15 Wider Context by Using Bilingual Language Models in Machine Translation
Jan Niehues, Teresa Herrmann, Stephan Vogel and Alex Waibel

15:15–15:40 A Minimally Supervised Approach for Detecting and Ranking Document Translation Pairs
Kriste Krstovski and David A. Smith

15:40–16:10 Coffee

Session 4: Syntax and Semantics (Chair: Michel Galley)

16:10–16:35 Agreement Constraints for Statistical Machine Translation into German
Philip Williams and Philipp Koehn

16:35–17:00 Fuzzy Syntactic Reordering for Phrase-based Statistical Machine Translation
Jacob Andreas, Nizar Habash and Owen Rambow

17:00–17:25 Filtering Antonymous, Trend-Contrasting, and Polarity-Dissimilar Distributional Paraphrases for Improving Statistical Machine Translation
Yuval Marton, Ahmed El Kholy and Nizar Habash

17:25–17:50 Productive Generation of Compound Words in Statistical Machine Translation
Sara Stymne and Nicola Cancedda

Sunday, July 31, 2011

Session 5: Machine Learning and Adaptation (Chair: Phil Blunsom)

9:00–10:25 SampleRank Training for Phrase-Based Machine Translation
Barry Haddow, Abhishek Arun and Philipp Koehn

9:25–10:50 Instance Selection for Machine Translation using Feature Decay Algorithms
Ergun Bicici and Deniz Yuret

9:50–10:15 Investigations on Translation Model Adaptation Using Monolingual Data
Patrik Lambert, Holger Schwenk, Christophe Servan and Sadaf Abdul-Rauf

10:15–10:40 Topic Adaptation for Lecture Translation through Bilingual Latent Semantic Models
Nick Ruiz and Marcello Federico

10:40–11:00 Coffee

Session 6: Shared Translation Task

11:00–12:40 Poster Presentations

Personal Translator at WMT2011
Vera Aleksic and Gregor Thurmair

LIMSI @ WMT11
Alexandre Allauzen, Hélène Bonneau-Maynard, Hai-Son Le, Aurélien Max, Guillaume Wisniewski, François Yvon, Gilles Adda, Josep Maria Crego, Adrien Lardilleux, Thomas Lavergne and Artem Sokolov

Shallow Semantic Trees for SMT
Wilker Aziz, Miguel Rios and Lucia Specia

RegMT System for Machine Translation, System Combination, and Evaluation
Ergun Bicici and Deniz Yuret

Improving Translation Model by Monolingual Data
Ondrej Bojar and Aleš Tamchyna

The CMU-ARK German-English Translation System
Chris Dyer, Kevin Gimpel, Jonathan H. Clark and Noah A. Smith

Noisy SMS Machine Translation in Low-Density Languages
Vladimir Eidelman, Kristy Hollingshead and Philip Resnik

Stochastic Parse Tree Selection for an Existing RBMT System
Christian Federmann and Sabine Hunsicker

Joint WMT Submission of the QUAERO Project
Markus Freitag, Gregor Leusch, Joern Wuebker, Stephan Peitz, Hermann Ney, Teresa Herrmann, Jan Niehues, Alex Waibel, Alexandre Allauzen, Gilles Adda, Josep Maria Crego, Bianka Buschbeck, Tonio Wandmacher and Jean Senellart

CMU Syntax-Based Machine Translation at WMT 2011
Greg Hanneman and Alon Lavie

The Uppsala-FBK systems at WMT 2011
Christian Hardmeier, Jörg Tiedemann, Markus Saers, Marcello Federico and Mathur Prashant

The Karlsruhe Institute of Technology Translation Systems for the WMT 2011
Teresa Herrmann, Mohammed Mediani, Jan Niehues and Alex Waibel

CMU Haitian Creole-English Translation System for WMT 2011
Sanjika Hewavitharana, Nguyen Bach, Qin Gao, Vamshi Ambati and Stephan Vogel

Experiments with word alignment, normalization and clause reordering for SMT between English and German
Maria Holmqvist, Sara Stymne and Lars Ahrenberg

The Value of Monolingual Crowdsourcing in a Real-World Translation Scenario: Simulation using Haitian Creole Emergency SMS Messages
Chang Hu, Philip Resnik, Yakov Kronrod, Vladimir Eidelman, Olivia Buzek and Benjamin B. Bederson

The RWTH Aachen Machine Translation System for WMT 2011
Matthias Huck, Joern Wuebker, Christoph Schmidt, Markus Freitag, Stephan Peitz, Daniel Stein, Arnaud Dagnelies, Saab Mansour, Gregor Leusch and Hermann Ney

ILLC-UvA translation system for EMNLP-WMT 2011
Maxim Khalilov and Khalil Sima’an

UPM system for the translation task
Verónica López-Ludeña and Rubén San-Segundo

Two-step translation with grammatical post-processing
David Mareček, Rudolf Rosa, Petra Galuščáková and Ondrej Bojar

Influence of Parser Choice on Dependency-Based MT
Martin Popel, David Mareček, Nathan Green and Zdenek Zabokrtsky

The LIGA (LIG/LIA) Machine Translation System for WMT 2011
Marion Potet, Raphaël Rubino, Benjamin Lecouteux, Stéphane Huet, Laurent Besacier, Hervé Blanchon and Fabrice Lefèvre

Factored Translation with Unsupervised Word Clusters
Christian Rishj and Anders Sgaard

The BM-I2R Haitian-Créole-to-English translation system description for the WMT 2011 evaluation campaign
Marta R. Costa-jussà and Rafael E. Banchs

The Universitat d'Alacant hybrid machine translation system for WMT 2011
Víctor M. Sánchez-Cartagena, Felipe Sánchez-Martínez and Juan Antonio Pérez-Ortiz

LIUM’s SMT Machine Translation Systems for WMT 2011
Holger Schwenk, Patrik Lambert, Loïc Barrault, Christophe Servan, Sadaf Abdul-Rauf, Haithem Afli and Kashif Shah

Spell Checking Techniques for Replacement of Unknown Words and Data Cleaning for Haitian Creole SMS Translation
Sara Stymne

Joshua 3.0: Syntax-based Machine Translation with the Thrax Grammar Extractor
Jonathan Weese, Juri Ganitkevitch, Chris Callison-Burch, Matt Post and Adam Lopez

DFKI Hybrid Machine Translation System for WMT 2011 - On the Integration of SMT and RBMT
Jia Xu, Hans Uszkoreit, Casey Kennington, David Vilar and Xiaojun Zhang

CEU-UPV English-Spanish system for WMT11
Francisco Zamora-Martinez and Maria Jose Castro-Bleda

Hierarchical Phrase-Based MT at the Charles University for the WMT 2011 Shared Task
Daniel Zeman

12:40–14:00 Lunch

Invited Talk

14:00–15:40 Crisis MT: Developing A Cookbook for MT in Crisis Situations
William Lewis, Robert Munro and Stephan Vogel

15:40–16:10 Coffee

Session 7: Translation Models (Chair: Chris Dyer)

16:10–16:35 Generative Models of Monolingual and Bilingual Gappy Patterns
Kevin Gimpel and Noah A. Smith

16:35–17:00 Extraction Programs: A Unified Approach to Translation Rule Extraction
Mark Hopkins, Greg Langmead and Tai Vo

17:00–17:25 Bayesian Extraction of Minimal SCFG Rules for Hierarchical Phrase-based Translation
Baskaran Sankaran, Gholamreza Haffari and Anoop Sarkar

17:25–17:50 From n-gram-based to CRF-based Translation Models
Thomas Lavergne, Alexandre Allauzen, Josep Maria Crego and François Yvon

EMNLP 2011 SIXTH WORKSHOP ON STATISTICAL MACHINE TRANSLATION