WMT16

Conference on Machine Translation


The First Conference on Machine Translation (WMT16) took place from 11 August to 12 August, 2016, in Berlin, Germany. It was organised by WMT.

statmt.org/wmt16/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

   
08:45 – 09:00 Opening Remarks
09:00 – 10:30 Session 1
Shared Tasks Overview Presentations I
09:00 – 09:20 Shared Task: News Translation
  Findings of the 2016 Conference on Machine Translation
Ondřej Bojar, Rajen Chatterjee, Christian Federmann, Yvette Graham, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Philipp Koehn, Varvara Logacheva, Christof Monz, Matteo Negri, Aurelie Neveol, Mariana Neves, Martin Popel, Matt Post, Raphael Rubino, Carolina Scarton, Lucia Specia, Marco Turchi, Karin Verspoor, Marcos Zampieri
09:20 – 09:35 Shared Task: IT-Domain Translation
09:35 – 09:50 Shared Task: Biomedical Translation
09:50 – 10:10 Shared Task: Metrics
  Results of the WMT16 Metrics Shared Task
Ondřej Bojar, Yvette Graham, Amir Kamran, Miloš Stanojević
10:10 – 10:30 Shared Task: Tuning
  Results of the WMT16 Tuning Shared Task
Bushra Jawaid, Amir Kamran, Miloš Stanojević, Ondřej Bojar
10:30 - 11:00 ☕️
11:00 – 12:30 Session 2: Shared Tasks Poster Session I
11:00 – 12:30 Shared Task: News Translation
  LIMSI@WMT’16: Machine Translation of News
Alexandre Allauzen, Lauriane Aufrant, Franck Burlot, Elena Knyazeva, Ophélie Lacroix, Thomas Lavergne, Guillaume Wisniewski, François Yvon
  TÜBİTAK SMT System Submission for WMT2016
Emre Bektaş, Ertuğrul Yilmaz, Coşkun Mermer, İlknur Durgar El-Kahlout
  ParFDA for Instance Selection for Statistical Machine Translation
Ergun Bicici
  Sheffield Systems for the English-Romanian WMT Translation Task
Frédéric Blain, Xingyi Song, Lucia Specia
  MetaMind Neural Machine Translation System for WMT 2016
James Bradbury, Richard Socher
  NYU-MILA Neural Machine Translation Systems for WMT’16
Junyoung Chung, Kyunghyun Cho, Yoshua Bengio
  The JHU Machine Translation Systems for WMT 2016
Shuoyang Ding, Kevin Duh, Huda Khayrallah, Philipp Koehn, Matt Post
  Yandex School of Data Analysis approach to English-Turkish translation at WMT16 News Translation Task
Anton Dvorkovich, Sergey Gubanov, Irina Galinskaya
  Hybrid Morphological Segmentation for Phrase-Based Machine Translation
Stig-Arne Grönroos, Sami Virpioja, Mikko Kurimo
  The AFRL-MITLL WMT16 News-Translation Task Systems
Jeremy Gwinnup, Tim Anderson, Grant Erdmann, Katherine Young, Michaeel Kazi, Elizabeth Salesky, Brian Thompson
  The Karlsruhe Institute of Technology Systems for the News Translation Task in WMT 2016
Thanh-Le Ha, Eunah Cho, Jan Niehues, Mohammed Mediani, Matthias Sperber, Alexandre Allauzen, Alexander Waibel
  The Edinburgh/LMU Hierarchical Machine Translation System for WMT 2016
Matthias Huck, Alexander Fraser, Barry Haddow
  The AMU-UEDIN Submission to the WMT16 News Translation Task: Attention-based NMT Models as Feature Functions in Phrase-based SMT
Marcin Junczys-Dowmunt, Tomasz Dwojak, Rico Sennrich
  NRC Russian-English Machine Translation System for WMT 2016
Chi-kiu Lo, Colin Cherry, George Foster, Darlene Stewart, Rabib Islam, Anna Kazantseva, Roland Kuhn
  Merged bilingual trees based on Universal Dependencies in Machine Translation
David Mareček
  PROMT Translation Systems for WMT 2016 Translation Tasks
Alexander Molchanov, Fedor Bykov
  The QT21/HimL Combined Machine Translation System
Jan-Thorsten Peter, Tamer Alkhouli, Hermann Ney, Matthias Huck, Fabienne Braune, Alexander Fraser, Aleš Tamchyna, Ondřej Bojar, Barry Haddow, Rico Sennrich, Frédéric Blain, Lucia Specia, Jan Niehues, Alex Waibel, Alexandre Allauzen, Lauriane Aufrant, Franck Burlot, Elena Knyazeva, Thomas Lavergne, François Yvon, Mārcis Pinnis, Stella Frank
  The RWTH Aachen University English-Romanian Machine Translation System for WMT 2016
Jan-Thorsten Peter, Tamer Alkhouli, Andreas Guta, Hermann Ney
  Abu-MaTran at WMT 2016 Translation Task: Deep Learning, Morphological Segmentation and Tuning on Character Sequences
Víctor M. Sánchez-Cartagena, Antonio Toral
  Edinburgh Neural Machine Translation Systems for WMT 16
Rico Sennrich, Barry Haddow, Alexandra Birch
  The Edit Distance Transducer in Action: The University of Cambridge English-German System at WMT16
Felix Stahlberg, Eva Hasler, Bill Byrne
  CUNI-LMU Submissions in WMT2016: Chimera Constrained and Beaten
Aleš Tamchyna, Roman Sudarikov, Ondřej Bojar, Alexander Fraser
  Phrase-Based SMT for Finnish with More Data, Better Models and Alternative Alignment and Translation Tools
Jörg Tiedemann, Fabienne Cap, Jenna Kanerva, Filip Ginter, Sara Stymne, Robert Östling, Marion Weller-Di Marco
  Edinburgh’s Statistical Machine Translation Systems for WMT16
Philip Williams, Rico Sennrich, Maria Nadejde, Matthias Huck, Barry Haddow, Ondřej Bojar
  PJAIT Systems for the WMT 2016
Krzysztof Wolk, Krzysztof Marasek
11:00 – 12:30 Shared Task: IT-domain Translation
  DFKI’s system for WMT16 IT-domain task, including analysis of systematic errors
Eleftherios Avramidis, Aljoscha Burchardt, Vivien Macketanz, Ankit Srivastava
  ILLC-UvA Adaptation System (Scorpio) at WMT’16 IT-DOMAIN Task
Hoang Cuong, Stella Frank, Khalil Sima’an
  Data Selection for IT Texts using Paragraph Vector
Mirela-Stefania Duma, Wolfgang Menzel
  SMT and Hybrid systems of the QTLeap project in the WMT16 IT-task
Rosa Gaudio, Gorka Labaka, Eneko Agirre, Petya Osenova, Kiril Simov, Martin Popel, Dieke Oele, Gertjan van Noord, Luís Gomes, João António Rodrigues, Steven Neale, João Silva, Andreia Querido, Nuno Rendeiro, António Branco
  JU-USAAR: A Domain Adaptive MT System
Koushik Pahari, Alapan Kuila, Santanu Pal, Sudip Kumar Naskar, Sivaji Bandyopadhyay, Josef van Genabith
  Dictionary-based Domain Adaptation of MT Systems without Retraining
Rudolf Rosa, Roman Sudarikov, Michal Novák, Martin Popel, Ondřej Bojar
11:00 – 12:30 Shared Task: Biomedical Translation
  English-Portuguese Biomedical Translation Task Using a Genuine Phrase-Based Statistical Machine Translation Approach
José Aires, Gabriel Lopes, Luís Gomes
  The TALP–UPC Spanish–English WMT Biomedical Task: Bilingual Embeddings and Char-based Neural Language Model Rescoring in a Phrase-based System
Marta R. Costa-jussà, Cristina España-Bonet, Pranava Madhyastha, Carlos Escolano, José A. R. Fonollosa
  LIMSI’s Contribution to the WMT’16 Biomedical Translation Task
Julia Ive, Aurélien Max, François Yvon
  IXA Biomedical Translation System at WMT16 Biomedical Translation Task
Olatz Perez-de-Viñaspre, Gorka Labaka
11:00 – 12:30 Shared Task: Metrics
  CobaltF: A Fluent Metric for MT Evaluation
Marina Fomicheva, Núria Bel, Lucia Specia, Iria da Cunha, Anton Malinovskiy
  DTED: Evaluation of Machine Translation Structure Using Dependency Parsing and Tree Edit Distance
Martin McCaffery, Mark-Jan Nederhof
  chrF deconstructed: beta parameters and n-gram weights
Maja Popović
  CharacTer: Translation Edit Rate on Character Level
Weiyue Wang, Jan-Thorsten Peter, Hendrik Rosendahl, Hermann Ney
  Extract Domain-specific Paraphrase from Monolingual Corpus for Automatic Evaluation of Machine Translation
Lilin Zhang, Zhen Weng, Wenyan Xiao, Jianyi Wan, Zhiming Chen, Yiming Tan, Maoxi Li, Mingwen Wang
11:00 – 12:30 Shared Task: Tuning
  Particle Swarm Optimization Submission for WMT16 Tuning Task
Viktor Kocur, Ondřej Bojar
12:30 – 14:00 🍴
14:00 – 15:30 Session 3: Invited Talk
Interactive Machine Translation: From Research to Practice
Spence Green
15:30 – 16:00 ☕️
16:00 – 17:40 Session 4: Research Papers on Linguistic Modelling
16:00 – 16:20 Cross-language Projection of Dependency Trees with Constrained Partial Parsing for Tree-to-Tree Machine Translation
Yu Shen, Chenhui Chu, Fabien Cromieres, Sadao Kurohashi
16:20 – 16:40 Improving Pronoun Translation by Modeling Coreference Uncertainty
Ngoc Quang Luong, Andrei Popescu-Belis
16:40 – 17:00 Modeling verbal inflection for English to German SMT
Anita Ramm, Alexander Fraser
17:00 – 17:20 Modeling Selectional Preferences of Verbs and Nouns in String-to-Tree Machine Translation
Maria Nadejde, Alexandra Birch, Philipp Koehn
17:20 – 17:40 Modeling Complement Types in Phrase-Based SMT
Marion Weller-Di Marco, Alexander Fraser, Sabine Schulte im Walde

Day 2

   
09:00 – 10:30 Session 5: Shared Tasks Overview Presentations II
09:00 – 9:20 Shared Task: Cross-Lingual Pronoun Prediction
  Findings of the 2016 WMT Shared Task on Cross-lingual Pronoun Prediction
Liane Guillou, Christian Hardmeier, Preslav Nakov, Sara Stymne, Jörg Tiedemann, Yannick Versley, Mauro Cettolo, Bonnie Webber, Andrei Popescu-Belis
09:20 – 09:45 Shared Task: Multimodal Machine Translation and Cross-Lingual Image Description
  A Shared Task on Multimodal Machine Translation and Crosslingual Image Description
Lucia Specia, Stella Frank, Khalil Sima’an, Desmond Elliott
09:45 – 10:00 Shared Task: Bilingual Document Alignment
  Findings of the WMT 2016 Bilingual Document Alignment Shared Task
Christian Buck, Philipp Koehn
10:00 – 10:15 Shared Task: Automatic Post-Editing
10:15 – 10:30 Shared Task: Quality Estimation
10:30 - 11:00 ☕️
11:00 – 12:30 Session 6: Shared Tasks Poster Session II
11:00 – 12:30 Shared Task: Cross-Lingual Pronoun Prediction
  Cross-lingual Pronoun Prediction with Linguistically Informed Features
Rachel Bawden
  The Kyoto University Cross-Lingual Pronoun Translation System
Raj Dabre, Yevgeniy Puzikov, Fabien Cromieres, Sadao Kurohashi
  Pronoun Prediction with Latent Anaphora Resolution
Christian Hardmeier
  It-disambiguation and source-aware language models for cross-lingual pronoun prediction
Sharid Loáiciga, Liane Guillou, Christian Hardmeier
  Pronoun Language Model and Grammatical Heuristics for Aiding Pronoun Prediction
Ngoc Quang Luong, Andrei Popescu-Belis
  Cross-Lingual Pronoun Prediction with Deep Recurrent Neural Networks
Juhani Luotolahti, Jenna Kanerva, Filip Ginter
  Pronoun Prediction with Linguistic Features and Example Weighing
Michal Novák
  Feature Exploration for Cross-Lingual Pronoun Prediction
Sara Stymne
  A Linear Baseline Classifier for Cross-Lingual Pronoun Prediction
Jörg Tiedemann
  Cross-lingual Pronoun Prediction for English, French and German with Maximum Entropy Classification
Dominikus Wetzel
11:00 – 12:30 Shared Task: Multimodal Machine Translation and Cross-Lingual Image Description
  Does Multimodality Help Human and Machine for Translation and Image Captioning?
Ozan Caglayan, Walid Aransa, Yaxing Wang, Marc Masana, Mercedes García-Martínez, Fethi Bougares, Loïc Barrault, Joost van de Weijer
  DCU-UvA Multimodal MT System Report
Iacer Calixto, Desmond Elliott, Stella Frank
  Attention-based Multimodal Neural Machine Translation
Po-Yao Huang, Frederick Liu, Sz-Rung Shiang, Jean Oh, Chris Dyer
  CUNI System for WMT16 Automatic Post-Editing and Multimodal Translation Tasks
Jindřich Libovický, Jindřich Helcl, Marek Tlustý, Ondřej Bojar, Pavel Pecina
  WMT 2016 Multimodal Translation System Description based on Bidirectional Recurrent Neural Networks with Double-Embeddings
Sergio Rodríguez Guasch, Marta R. Costa-jussà
  SHEF-Multimodal: Grounding Machine Translation on Images
Kashif Shah, Josiah Wang, Lucia Specia
11:00 – 12:30 Shared Task: Bilingual Document Alignment
  DOCAL - Vicomtech’s Participation in the WMT16 Shared Task on Bilingual Document Alignment
Andoni Azpeitia, Thierry Etchegoyhen
  Quick and Reliable Document Alignment via TF/IDF-weighted Cosine Distance
Christian Buck, Philipp Koehn
  YODA System for WMT16 Shared Task: Bilingual Document Alignment
Aswarth Abhilash Dara, Yiu-Chang Lin
  Bitextor’s participation in WMT’16: shared task on document alignment
Miquel Esplà-Gomis, Mikel Forcada, Sergio Ortiz Rojas, Jorge Ferrández-Tordera
  Bilingual Document Alignment with Latent Semantic Indexing
Ulrich Germann
  First Steps Towards Coverage-Based Document Alignment
Luís Gomes, Gabriel Pereira Lopes
  BAD LUC@WMT 2016: a Bilingual Document Alignment Platform Based on Lucene
Laurent Jakubina, Phillippe Langlais
  Using Term Position Similarity and Language Modeling for Bilingual Document Alignment
Thanh Le, Hoa Trong Vu, Jonathan Oberländer, Ondřej Bojar
  The ADAPT Bilingual Document Alignment system at WMT16
Pintu Lohar, Haithem Afli, Chao-Hong Liu, Andy Way
  WMT2016: A Hybrid Approach to Bilingual Document Alignment
Sainik Mahata, Dipankar Das, Santanu Pal
  English-French Document Alignment Based on Keywords and Statistical Translation
Marek Medveď, Miloš Jakubíček, Vojtech Kovář
  The ILSP/ARC submission to the WMT 2016 Bilingual Document Alignment Shared Task
Vassilis Papavassiliou, Prokopis Prokopidis, Stelios Piperidis
  Word Clustering Approach to Bilingual Document Alignment (WMT 2016 Shared Task)
Vadim Shchukin, Dmitry Khristich and Irina Galinskaya
11:00 – 12:30 Shared Task: Automatic Post-Editing
  The FBK Participation in the WMT 2016 Automatic Post-editing Shared Task
Rajen Chatterjee, José G. C. de Souza, Matteo Negri, Marco Turchi
  Log-linear Combinations of Monolingual and Bilingual Neural Machine Translation Models for Automatic Post-Editing
Marcin Junczys-Dowmunt, Roman Grundkiewicz
  USAAR: An Operation Sequential Model for Automatic Statistical Post-Editing
Santanu Pal, Marcos Zampieri, Josef van Genabith
11:00 – 12:30 Shared Task: Quality Estimation
  Bilingual Embeddings and Word Alignments for Translation Quality Estimation
Amal Abdelsalam, Ondřej Bojar, Samhaa El-Beltagy
  SHEF-MIME: Word-level Quality Estimation Using Imitation Learning
Daniel Beck, Andreas Vlachos, Gustavo Paetzold, Lucia Specia
  Referential Translation Machines for Predicting Translation Performance
Ergun Biçici
  UAlacant word-level and phrase-level machine translation quality estimation systems at WMT 2016
Miquel Esplà-Gomis, Felipe Sánchez-Martínez, Mikel Forcada
  Recurrent Neural Network based Translation Quality Estimation
Hyun Kim, Jong-Hyeok Lee
  YSDA Participation in the WMT’16 Quality Estimation Shared Task
Anna Kozlova, Mariya Shmatova, Anton Frolov
  USFD’s Phrase-level Quality Estimation Systems
Varvara Logacheva, Frédéric Blain, Lucia Specia
  Unbabel’s Participation in the WMT16 Word-Level Translation Quality Estimation Shared Task
André F. T. Martins, Ramón Astudillo, Chris Hokamp, Fabio Kepler
  SimpleNets: Quality Estimation with Resource-Light Neural Networks
Gustavo Paetzold, Lucia Specia
  Translation Quality Estimation using Recurrent Neural Network
Raj Nath Patel, Sasikumar M
  The UU Submission to the Machine Translation Quality Estimation Task
Oscar Sagemo, Sara Stymne
  Word embeddings and discourse information for Quality Estimation
Carolina Scarton, Daniel Beck, Kashif Shah, Karin Sim Smith, Lucia Specia
  SHEF-LIUM-NN: Sentence level Quality Estimation with Neural Network Features
Kashif Shah, Fethi Bougares, Loïc Barrault, Lucia Specia
  UGENT-LT3 SCATE Submission for WMT16 Shared Task on Quality Estimation
Arda Tezcan, Véronique Hoste, Lieve Macken
12:30 – 14:00 🍴
14:00 – 15:20 Session 7: Research Papers on Neural Translation
14:00 – 14:20 Alignment-Based Neural Machine Translation
Tamer Alkhouli, Gabriel Bretschner, Jan-Thorsten Peter, Mohammed Hethnawi, Andreas Guta, Hermann Ney
14:20 – 14:40 Neural Network-based Word Alignment through Score Aggregation
Joël Legrand, Michael Auli, Ronan Collobert
14:40 – 15:00 Using Factored Word Representation in Neural Network Language Models
Jan Niehues, Thanh-Le Ha, Eunah Cho, Alex Waibel
15:00 – 15:20 Linguistic Input Features Improve Neural Machine Translation
Rico Sennrich, Barry Haddow
15:30 – 16:00 ☕️
16:00 – 17:20 Session 8: Research Papers on Translation Models
16:00 – 16:20 A Framework for Discriminative Rule Selection in Hierarchical Moses
Fabienne Braune, Alexander Fraser, Hal Daumé III, Aleš Tamchyna
16:00 – 16:40 Fast and highly parallelizable phrase table for statistical machine translation
Nikolay Bogoychev, Hieu Hoang
16:00 – 17:00 A Comparative Study on Vocabulary Reduction for Phrase Table Smoothing
Yunsu Kim, Andreas Guta, Joern Wuebker, Hermann Ney
17:00 – 17:20 Examining the Relationship between Preordering and Word Order Freedom in Machine Translation
Joachim Daiber, Miloš Stanojević, Wilker Aziz, Khalil Sima’an

Results

Full results of the shared tasks: Findings of the 2016 Conference on Machine Translation (WMT16)

News translation

The results were determined with a relative ranking through the TrueSkill model.

→ English

Language pair System Score
Czech → UEDIN-NMT 0.62
Romanian → ONLINE-B 0.58
German → UEDIN-NMT 0.82
Russian → AMU-UEDIN 0.45
Turkish → ONLINE-B 0.82
Finnish → UEDIN-PBMT 0.42

English →

Language pair System Score
→ Czech UEDIN-NMT 0.59
→ Romanian UEDIN-NMT 0.45
→ German UEDIN-NMT 0.49
→ Russian PROMT-RULE 0.79
→ Turkish ONLINE-G 0.76
→ Finnish ONLINE-G 0.36

Want to learn more about WMT16?


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 →