WMT10

Workshop on Machine Translation

---

Location

• Uppsala, Sweden

Links

• statmt.org/wmt10/program.html

Shared Tasks

• Translation
• System combination
• Evaluation

Schedule

Day 1

8:45	Opening Remarks
9:00	Full Paper Session 1 A Semi-Supervised Word Alignment Algorithm with Partial Manual Alignments Qin Gao, Nguyen Bach, Stephan Vogel
9:25	Fast Consensus Hypothesis Regeneration for Machine Translation Boxing Chen, George Foster, Roland Kuhn
9:50	Fast Consensus Hypothesis Regeneration for Machine Translation Boxing Chen, George Foster, Roland Kuhn
10:15	Boaster Session 1: Translation Task
10:45	☕️
	Poster Session: Translation Task
	LIMSI’s Statistical Translation Systems for WMT’10 Alexandre Allauzen, Josep M. Crego, I°lknur Durgar El-Kahlout, Francois Yvon
	2010 Failures in English-Czech Phrase-Based MT Ondrej Bojar, Kamil Kos
	An Empirical Study on Development Set Selection Strategy for Machine Translation Learning Hui Cong, Zhao Hai, Lu Bao-Liang, Song Yan
	The University of Maryland Statistical Machine Translation System for the Fifth Workshop on Machine Translation Vladimir Eidelman, Chris Dyer, Philip Resnik
	Further Experiments with Shallow Hybrid MT Systems Christian Federmann, Andreas Eisele, Yu Chen, Sabine Hunsicker, Jia Xu, Hans Uszkoreit
	Improved Features and Grammar Selection for Syntax-Based MT Greg Hanneman, Jonathan Clark, Alon Lavie
	FBK at WMT 2010: Word Lattices for Morphological Reduction and Chunk-Based Reordering Christian Hardmeier, Arianna Bisazza, Marcello Federico
	The RWTH Aachen Machine Translation System for WMT 2010 Carmen Heger, Joern Wuebker, Matthias Huck, Gregor Leusch, Saab Mansour, Daniel Stein, Hermann Ney
	Using Collocation Segmentation to Augment the Phrase Table Carlos A. Henríquez Q., Marta Ruiz Costa-jussà, Vidas Daudaravicius, Rafael E. Banchs, José B. Mariño
	The RALI Machine Translation System for WMT 2010 Stéphane Huet, Julien Bourdaillet, Alexandre Patry, Philippe Langlais
	Exodus - Exploring SMT for EU Institutions Michael Jellinghaus, Alexandros Poulis, David Kolovratník
	More Linguistic Annotation for Statistical Machine Translation Philipp Koehn, Barry Haddow, Philip Williams, Hieu Hoang
	LIUM SMT Machine Translation System for WMT 2010 Patrik Lambert, Sadaf Abdul-Rauf, Holger Schwenk
	Lessons from NRC’s Portage System at WMT 2010 Samuel Larkin, Boxing Chen, George Foster, Ulrich Germann, Eric Joanis, Howard Johnson, Roland Kuhn
	Joshua 2.0: A Toolkit for Parsing-Based Machine Translation with Syntax, Semirings, Discriminative Training and Other Goodies Zhifei Li, Chris Callison-Burch, Chris Dyer, Juri Ganitkevitch, Ann Irvine, Sanjeev Khudanpur, Lane Schwartz, Wren Thornton, Ziyuan Wang, Jonathan Weese, Omar Zaidan
	The Karlsruhe Institute for Technology Translation System for the ACL-WMT 2010 Jan Niehues, Teresa Herrmann, Mohammed Mediani, Alex Waibel
	MATREX: The DCU MT System for WMT 2010 Sergio Penkale, Rejwanul Haque, Sandipan Dandapat, Pratyush Banerjee, Ankit K. Srivastava, Jinhua Du, Pavel Pecina, Sudip Kumar Naskar, Mikel L. Forcada, Andy Way
	The Cunei Machine Translation Platform for WMT ’10 Aaron Phillips
	The CUED HiFST System for the WMT10 Translation Shared Task Juan Pino, Gonzalo Iglesias, Adrià de Gispert, Graeme Blackwood, Jamie Brunning, William Byrne
	The LIG Machine Translation System for WMT 2010 Marion Potet, Laurent Besacier, Hervé Blanchon
	Linear Inversion Transduction Grammar Alignments as a Second Translation Path Markus Saers, Joakim Nivre, Dekai Wu
	UPV-PRHLT English–Spanish System for WMT10 Germán Sanchis-Trilles, Jesús Andrés-Ferrer, Guillem Gascó, Jesús González-Rubio, Pascual Martínez-Gómez, Martha-Alicia Rocha, Joan-Andreu Sánchez, Francisco Casacuberta
	Reproducible Results in Parsing-Based Machine Translation: The JHU Shared Task Submission Lane Schwartz
	Vs and OOVs: Two Problems for Translation between German and English Sara Stymne, Maria Holmqvist, Lars Ahrenberg
	To Cache or Not To Cache? Experiments with Adaptive Models in Statistical Machine Translation Jörg Tiedemann
	Applying Morphological Decompositions to Statistical Machine Translation Sami Virpioja, Jaakko Väyrynen, Andre Mansikkaniemi, Mikko Kurimo
	Maximum Entropy Translation Model in Dependency-Based MT Framework ZdenÄ›k Žabokrtský, Martin Popel, David Mareček
	UCH-UPV English–Spanish System for WMT10 Francisco Zamora-Martinez, Germán Sanchis-Trilles
	Hierarchical Phrase-Based MT at the Charles University for the WMT 2010 Shared Task Daniel Zeman
12:30	🍴
14:00	Invited Talk Hermann Ney
15:05	Full Paper Session 2 Incremental Decoding for Phrase-Based Statistical Machine Translation Baskaran Sankaran, Ajeet Grewal, Anoop Sarkar
15:30	☕️
16:00	Full Paper Session 3 How to Avoid Burning Ducks: Combining Linguistic Analysis and Corpus Statistics for German Compound Processing Fabienne Fritzinger, Alexander Fraser
16:25	Chunk-Based Verb Reordering in VSO Sentences for Arabic-English Statistical Machine Translation Arianna Bisazza, Marcello Federico
16:50	Head Finalization: A Simple Reordering Rule for SOV Languages Hideki Isozaki, Katsuhito Sudoh, Hajime Tsukada, Kevin Duh
17:15	Aiding Pronoun Translation with Co-Reference Resolution Ronan Le Nagard, Philipp Koehn

Day 2

9:00	Shared Task Presentations Overview: MetricsMATR (slides)
10:00	Discussion
10:30	Boaster Session
10:45	☕️
	Poster Session: Full Paper
	Jane: Open Source Hierarchical Translation, Extended with Reordering and Lexicon Models David Vilar, Daniel Stein, Matthias Huck, Hermann Ney
	Poster Session: System Combination Task
	MANY: Open Source MT System Combination at WMT’10 Loïc Barrault
	Adaptive Model Weighting and Transductive Regression for Predicting Best System Combinations Ergun Bicici, S. Serdar Kozat
	L1 Regularized Regression for Reranking and System Combination in Machine Translation Ergun Bicici, Deniz Yuret
	An Augmented Three-Pass System Combination Framework: DCU Combination System for WMT 2010 Jinhua Du, Pavel Pecina, Andy Way
	The UPV-PRHLT Combination System for WMT 2010 Jesús González-Rubio, Germán Sanchis-Trilles, Joan-Andreu Sánchez, Jesús Andrés-Ferrer, Guillem Gascó, Pascual Martínez-Gómez, Martha-Alicia Rocha, Francisco Casacuberta
	CMU Multi-Engine Machine Translation for WMT 2010 Kenneth Heafield, Alon Lavie
	CMU System Combination via Hypothesis Selection for WMT’10 Almut Silja Hildebrand, Stephan Vogel
	JHU System Combination Scheme for WMT 2010 Sushant Narsale
	The RWTH System Combination System for WMT 2010 Gregor Leusch, Hermann Ney
	BBN System Description for WMT10 System Combination Task Antti-Veikko Rosti, Bing Zhang, Spyros Matsoukas, Richard Schwartz
	Poster Session: Metrics Task
	LRscore for Evaluating Lexical and Reordering Quality in MT Alexandra Birch, Miles Osborne
	Document-Level Automatic MT Evaluation based on Discourse Repreentations Elisabet Comelles, Jesus Gimenez, Lluis Marquez, Irene Castellon, Victoria Arranz
	METEOR-NEXT and the METEOR Paraphrase Tables: Improved Evaluation Support for Five Target Languages Michael Denkowski, Alon Lavie
	Normalized Compression Distance Based Measures for MetricsMATR 2010 Marcus Dobrinkat, Tero Tapiovaara, Jaakko Väyrynen, Kimmo Kettunen
	The DCU Dependency-Based Metric in WMT-MetricsMATR 2010 Yifan He, Jinhua Du, Andy Way, Josef van Genabith
	TESLA: Translation Evaluation of Sentences with Linear-Programming-Based Analysis Chang Liu, Daniel Dahlmeier, Hwee Tou Ng
	The Parameter-Optimized ATEC Metric for MT Evaluation Billy Wong, Chunyu Kit
12:30	🍴
14:00	Full Paper Session 4 A Unified Approach to Minimum Risk Training and Decoding Abhishek Arun, Barry Haddow, Philipp Koehn
14:25	N-Best Reranking by Multitask Learning Kevin Duh, Katsuhito Sudoh, Hajime Tsukada, Hideki Isozaki, Masaaki Nagata
14:50	Taming Structured Perceptrons on Wild Feature Vectors Ralf Brown
15:15	Translation Model Adaptation by Resampling Kashif Shah, Loïc Barrault, Holger Schwenk
15:40	☕️
16:00	Full Paper Session 5 Integration of Multiple Bilingually-Learned Segmentation Schemes into Statistical Machine Translation Michael Paul, Andrew Finch, Eiichiro Sumita
16:25	Improved Translation with Source Syntax Labels Hieu Hoang, Philipp Koehn
16:50	Divide and Translate: Improving Long Distance Reordering in Statistical Machine Translation Katsuhito Sudoh, Kevin Duh, Hajime Tsukada, Tsutomu Hirao, Masaaki Nagata
17:15	Decision Trees for Lexical Smoothing in Statistical Machine Translation Rabih Zbib, Spyros Matsoukas, Richard Schwartz, John Makhoul

Results

General Task

Full results of the shared task: Findings of the 2010 Joint Workshop on Statistical Machine Translation and Metrics for Machine Translatio

News translation

The results were determined with a relative ranking, the ≥ others (“greater than or equal to others”) score.

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

→ English

Language pair	System	≥ others
French →	LIUM ONLINE-B NRC CAMBRIDGE LIMSI RALI RWTH	0.71 0.71 0.66 0.66 0.65 0.65 0.55
German →	ONLINE-B KIT UMD UEDIN FBK ONLINE-A	0.73 0.72 0.68 0.66 0.66 0.63
Spanish →	ONLINE-B UEDIN UPC	0.70 0.69 0.51
Czech →	ONLINE-B UEDIN	0.70 0.61

English →

Language pair	System	≥ others
→ French	UEDIN ONLINE-B RALI LIMSI RWTH CAMBRIDGE	0.70 0.68 0.66 0.66 0.63 0.63
→ German	ONLINE-B DFKI UEDIN KIT FBK	0.70 0.62 0.62 0.60 0.56
→ Spanish	ONLINE-B ONLINE-A UEDIN DFKI JHU UPV CAMBRIDGE UHC-UPV	0.71 0.69 0.61 0.55 0.55 0.55 0.54 0.54
→ Czech	ONLINE-B CU-BOJAR PC-TRANS UEDIN	0.70 0.66 0.62 0.62