Skip to main content

QT21: Quality Translation 21

Deliverables

Semantics in Shallow Models

This Deliverable describes the results of the Task T1.2, in the form of papers published at major conferences complemented by a summary of those results. It will be available at M18 as a preliminary report, and updated at M36 (final version).

Semantics in Shallow Models (Final vn)

This Deliverable describes the results of the Task T1.2, in the form of papers published at major conferences complemented by a summary of those results. It will be available at M18 as a preliminary report, and updated at M36 (final version).

Improved Learning for Machine Translation (Final vn)

This Deliverable describes the results of the Task T1.3, in the form of papers published at major conferences complemented by a summary of those results. It will be available at M18 as a preliminary report, and updated at M36 (final version).

Public Progress Report (M19-36)

Publishable summary of project results and impact during the second period.

Report on the Third Quality Translation Shared Task

Report on the Third Quality Translation Shared Task (UEDIN, M36)

Final Report: Under-resourced languages

This report will summarize our work on improving translation quality for under-resources languages. It will contain models to improve learning on other knowledge sources as well as improving the usage of small amounts of available parallel data.

Quality Estimation Metrics and Analysis of Second Annotation Round and Error Profiles

This deliverable will evaluate the results of MT output from improved systems, comparing it to the results from D3.3, and the progress on fine-grained quality estimation models. It will also report on error profiles identified in the source and target languages, along with a recommendation for how to implement these in an automatic fashion. The report will address the significance of the factors identified and provide hypotheses for future testing in additional languages not covered in QT21. It will include an updated comprehensive database with annotated segments from both rounds of annotation.

Human-informed Continuous Learning: Report 3: Leveraging post-editing + Year 2 annotations

Continuous learning will focus on the three levels (upstream, MT system, downstream) in coordination with the other two WP3 tasks. Research and reporting timing will be synchronised with the availability to the project of annotated data (T3.1) and diagnostic tools (T3.2). M36: upstream/MT/downstream-level components leveraging post editions and Year2 error annotations. Each deliverable will report the progress on each task along the three years of the project.

Intermediate Report: Morphologically rich languages

This deliverable will report first experiments on modelling words in morphologically rich languages.

Report on the First Quality Translation Shared Task

Report on the First Quality Translation Shared Task (UEDIN, M12)

Final Report: Morphologically rich languages

This deliverable will summarize all approaches that have been investigated in this project to improve translation quality on tasks involving morphologically rich languages.

Improved Learning for Machine Translation

This Deliverable describes the results of the Task T1.3, in the form of papers published at major conferences complemented by a summary of those results. It will be available at M18 as a preliminary report, and updated at M36 (final version).

Evaluation Metrics and Analysis of First Annotation Round

This deliverable will report on the results of the first annotation round, including error profiles for each language pair and a comparison of the results with analysis based on post-edited examples. It will also include a database of the annotated data for use in training systems and for further analysis and a listing and analysis of measurable factors (semantics and linguistics analyses) found in the annotation done in T3.1 that correspond to human quality judgments. This deliverable will also evaluate the progress on syntax and semantic-informed evaluation metrics.

Harmonised Error Metric

The harmonised metric will consist of a union of the MQM error type hierarchy and the DQF analytic metric. The harmonisation will involve the addition of necessary categories from DQF to MQM and the adoption of shared terminology. TAUS will determine which categories (if any) to add to DQF from the MQM master hierarchy. The result will be a joint publication of the results and use of the harmonised terminology for error types in both MQM and DQF. The harmonised metric will be tested on a set of approximately 300 segments of EN>DE data taken from T3.1 with triple annotation to ensure that annotators are able to deploy the metric correctly and to suggest improvements to training materials. Testing will be conducted in cooperation with GALA. The result will be a report on agreement and suggestion for any needed changes to the metric profile chosen to be used in subsequent tasks.

Human-informed Continuous Learning: Report 1: Leveraging post-editing

Continuous learning will focus on the three levels (upstream, MT system, downstream) in coordination with the other two WP3 tasks. Research and reporting timing will be synchronised with the availability to the project of annotated data (T3.1) and diagnostic tools (T3.2). M12: downstream-level component leveraging post editions. Each deliverable will report the progress on each task along the three years of the project.

Human-informed Continuous Learning: Report 2: Leveraging post-editing + Year 1 annotations

Continuous learning will focus on the three levels (upstream, MT system, downstream) in coordination with the other two WP3 tasks. Research and reporting timing will be synchronised with the availability to the project of annotated data (T3.1) and diagnostic tools (T3.2). M24: upstream/MT/downstream-level components leveraging post editions and Year1 error annotations. Each deliverable will report the progress on each task along the three years of the project.

Data Management Plan

D5.5 Data Management Plan (DFKI, M06)

Semantic Translation Models

This Deliverable describes the results of the Task T1.1, in the form of papers published at major conferences complemented by a summary of those results. It will be available at M18 as a preliminary report, and updated at M36 (final version).

Intermediate Report: Under-resourced languages

This report will summarize the efforts to improve state-of-the-art translation systems for under-resourced languages. It will describe the approaches to learn translation rules from other data sources than parallel data.

Data Management Plan Update

D5.6 Data Management Plan Update (DFKI, M18)

Public Progress Report (M1-18))

Publishable summary of project results and impact during the first period.

Report on the Second Quality Translation Shared Task

Report on the Second Quality Translation Shared Task (UEDIN, M24)

Data Management Plan Update (Final vn)

D5.7 Data Management Plan Update (DFKI, M30)

Semantic Translation Models (Final vn)

This Deliverable describes the results of the Task T1.1, in the form of papers published at major conferences complemented by a summary of those results. It will be available at M18 as a preliminary report, and updated at M36 (final version).

Data Collection: Resources and Tools

Collected data, and description of data collection procedure in terms of protocols and guidelines for human annotators and interface functionalities of the tools needed for the collection will be presented in this deliverable. The amount and type of information and annotation acquired will be reported for each language pair involved in WP3.

Searching for OpenAIRE data...

Publications

Paying Attention to Multi-Word Expressions in Neural Machine Translation

Author(s): Rikters, Matīss; Bojar, Ondřej
Published in: Proceedings of MT Summit XVI (IAMT), Issue 1, 2017

Source Discriminative Word Lexicon for Translation Disambiguation




UFAL Submissions to the IWSLT 2016 MT Track

Author(s): Kocmi, Tom; Helcl, Jindřich; Bojar, Ondřej; Sudarikov, Roman; Cífka, Ondřej
Published in: Issue 2, 2016

English to Irish Machine Translation with Automatic Post-Editing




Neural Machine Translation of Rare Words with Subword Units

Author(s): Rico Sennrich, Barry Haddow, Alexandra Birch
Published in: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2016, Page(s) 1715-1725
DOI: 10.18653/v1/P16-1162

Two-Step MT: Predicting Target Morphology

Author(s): Burlot, Franck; Knyazeva, Elena; Lavergne, Thomas; Yvon, François
Published in: https://hal.archives-ouvertes.fr/hal-01592337, Issue 2, 2016

Variable Mini-Batch Sizing and Pre-Trained Embeddings

Author(s): Bojar, Ondřej; Abdou, Mostafa; Glončák, Vladan
Published in: Issue 2, 2017

Zero-resource Dependency Parsing: Boosting Delexicalized Cross-lingual Transfer with Linguistic Knowledge

Author(s): Aufrant, Lauriane; Wisniewski, Guillaume; Yvon, François
Published in: Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, Issue 2, 2016

Multi30K: Multilingual English-German Image Descriptions

Author(s): Desmond Elliott, Stella Frank, Khalil Sima'an, Lucia Specia
Published in: Proceedings of the 5th Workshop on Vision and Language, 2016, Page(s) 70-74
DOI: 10.18653/v1/W16-3210

Linguistic Input Features Improve Neural Machine Translation

Author(s): Rico Sennrich, Barry Haddow
Published in: Proceedings of the First Conference on Machine Translation: Volume 1, Research Papers, 2016, Page(s) 83-91
DOI: 10.18653/v1/W16-2209

CUNI System for the WMT17 Multimodal Translation Task

Author(s): Libovický, Jindřich; Helcl, Jindřich
Published in: Issue 2, 2017

DCU-UvA Multimodal MT System Report

Author(s): Iacer Calixto, Desmond Elliott, Stella Frank
Published in: Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers, 2016, Page(s) 634-638
DOI: 10.18653/v1/W16-2359

The KIT Translation Systems for IWSLT 2015




Evaluating the morphological competence of Machine Translation Systems

Author(s): Burlot, Franck; Yvon, François
Published in: https://hal.archives-ouvertes.fr/hal-01618387, Issue 1, 2017, Page(s) 43--55

Attention Strategies for Multi-Source Sequence-to-Sequence Learning

Author(s): Libovický, Jindřich; Helcl, Jindřich
Published in: Issue 1, 2017, Page(s) 196--202

Manual and Automatic Paraphrases for MT Evaluation

Author(s): Tamchyna, Aleš; Barančíková, Petra
Published in: 3543-3548 (2016)., Issue 2, 2016

Machine Translation with Source-Predicted Target Morphology




Verb Sense Disambiguation in Machine Translation

Author(s): Kríž, Vincent; Dušek, Ondřej; Bojar, Ondřej; Sudarikov, Roman; Holub, Martin
Published in: Issue 2, 2016, Page(s) 42--50

Exploring Prediction Uncertainty in Machine Translation Quality Estimation

Author(s): Daniel Beck, Lucia Specia, Trevor Cohn
Published in: Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning, 2016, Page(s) 208-218
DOI: 10.18653/v1/K16-1021

A Shared Task on Multimodal Machine Translation and Crosslingual Image Description

Author(s): Lucia Specia, Stella Frank, Khalil Sima'an, Desmond Elliott
Published in: Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers, 2016, Page(s) 543-553
DOI: 10.18653/v1/W16-2346

A Discriminative Training Procedure for Continuous Translation Models

Author(s): Quoc-Khanh DO, Alexandre Allauzen, François Yvon
Published in: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, 2015, Page(s) 1046-1052
DOI: 10.18653/v1/D15-1121

Curriculum Learning and Minibatch Bucketing in Neural Machine Translation

Author(s): Kocmi, Tom; Bojar, Ondřej
Published in: Issue 1, 2017

The Edinburgh/JHU Phrase-based Machine Translation Systems for WMT~2015

Author(s): Barry Haddow, Matthias Huck, Alexandra Birch, Nikolay Bogoychev, Philipp Koehn
Published in: Proceedings of the Tenth Workshop on Statistical Machine Translation, 2015, Page(s) 126-133
DOI: 10.18653/v1/W15-3013

Cross-lingual alignment transfer: a chicken-and-egg story?

Author(s): Lauriane Aufrant, Guillaume Wisniewski, François Yvon
Published in: Proceedings of the Workshop on Multilingual and Cross­-lingual Methods in NLP, 2016, Page(s) 35-44
DOI: 10.18653/v1/W16-1205

LIMSI@WMT'17

Author(s): Burlot, Franck; Safari, Pooyan; Labeau, Matthieu; Allauzen, Alexandre; Yvon, François
Published in: https://hal.archives-ouvertes.fr/hal-01619897, Issue 2, 2017

Edinburgh Neural Machine Translation Systems for WMT 16

Author(s): Rico Sennrich, Barry Haddow, Alexandra Birch
Published in: Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers, 2016, Page(s) 371-376
DOI: 10.18653/v1/W16-2323

The RWTH Aachen University English-Romanian Machine Translation System for WMT 2016

Author(s): Jan-Thorsten Peter, Tamer Alkhouli, Andreas Guta, Hermann Ney
Published in: Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers, 2016, Page(s) 356-361
DOI: 10.18653/v1/W16-2321

Modeling Selectional Preferences of Verbs and Nouns in String-to-Tree Machine Translation

Author(s): Maria Nadejde, Alexandra Birch, Philipp Koehn
Published in: Proceedings of the First Conference on Machine Translation: Volume 1, Research Papers, 2016, Page(s) 32-42
DOI: 10.18653/v1/W16-2204

Morphology-Aware Alignments for Translation to and from a Synthetic Language




Bilingual Embeddings and Word Alignments for Translation Quality Estimation

Author(s): Amal Abdelsalam, Ondřej Bojar, Samhaa El-Beltagy
Published in: Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers, 2016, Page(s) 764-771
DOI: 10.18653/v1/W16-2380

Unsupervised learning of morphology in the USSR




Towards cross-lingual distributed representations without parallel text trained with adversarial autoencoders

Author(s): Antonio Valerio Miceli Barone
Published in: Proceedings of the 1st Workshop on Representation Learning for NLP, 2016, Page(s) 121-126
DOI: 10.18653/v1/W16-1614

Particle Swarm Optimization Submission for WMT16 Tuning Task

Author(s): Viktor Kocur, Ondřej Bojar
Published in: Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers, 2016, Page(s) 518-524
DOI: 10.18653/v1/W16-2344

Splitting Compounds by Semantic Analogy

Author(s): Daiber, Joachim; Quiroz, Lautaro; Wechsler, Roger; Frank, Stella
Published in: Praha : Charles University in Prague, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics, 20-28 (2015)., Issue 2, 2015, Page(s) 20--28

SubGram: Extending Skip-gram Word Representation with Substrings

Author(s): Kocmi, Tom; Bojar, Ondřej
Published in: Issue 2, 2016, Page(s) 182--189
DOI: 10.1007/978-3-319-45510-5_21

The QT21 Combined Machine Translation System for English to Latvian

Author(s): Niehues, Jan; Sics, Valters; Pham, Ngoc-Quam; Aziz, Wilker; Blain, Frédéric; Bastings, Joost; Williams, Phil; Peter, Jan-Thorsten; Specia, Lucia; Rios, Miguel; Pinnis, Marcis; Yvon, François; Waibel, Alex; Burlot, Franck; Bojar, Ondřej; Ney, Hermann
Published in: Issue 2, 2017

Results of the WMT17 Neural MT Training Task

Author(s): Libovický, Jindřich; Musil, Tomáš; Kocmi, Tom; Helcl, Jindřich; Bojar, Ondřej
Published in: Issue 2, 2017

Word Representations in Factored Neural Machine Translation

Author(s): Burlot, Franck; Garcia-Martinez, Mercedes; Bougares, Fethi; Barrault, Loïc; Yvon, François
Published in: https://hal.archives-ouvertes.fr/hal-01618384, Issue 1, 2017, Page(s) 257--264

CUNI Neural Experiments

Author(s): Libovický, Jindřich; Kocmi, Tom; Helcl, Jindřich; Bojar, Ondřej; Mareček, David
Published in: Issue 1, 2017

CUNI-LMU Submissions in WMT2016: Chimera Constrained and Beaten

Author(s): Aleš Tamchyna, Roman Sudarikov, Ondřej Bojar, Alexander Fraser
Published in: Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers, 2016, Page(s) 385-390
DOI: 10.18653/v1/W16-2325

USFD’s Phrase-level Quality Estimation Systems

Author(s): Varvara Logacheva, Frédéric Blain, Lucia Specia
Published in: Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers, 2016, Page(s) 800-805
DOI: 10.18653/v1/W16-2386

Phrase Level Segmentation and Labelling of Machine Translation Errors

Author(s): Logacheva, Varvara; Specia, Lucia; Blain, Frédéric
Published in: Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016) 10th edition of the Language Resources and Evaluation Conference - LREC, LREC 2016, Portorož, Slovenia, 2016-05-23 - 2016-05-28 , Issue 7, 2016

BIRA: Improved Predictive Exchange Word Clustering

Author(s): Jon Dehdari, Liling Tan, Josef van Genabith
Published in: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2016, Page(s) 1169-1174
DOI: 10.18653/v1/N16-1139

Exponentially Decaying Bag-of-Words Input Features for Feed-Forward Neural Network in Statistical Machine Translation

Author(s): Jan-Thorsten Peter, Weiyue Wang, Hermann Ney
Published in: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 2016, Page(s) 293-298
DOI: 10.18653/v1/P16-2048

FBK HLT-MT at SemEval-2016 Task 1: Cross-lingual Semantic Similarity Measurement Using Quality Estimation Features and Compositional Bilingual Word Embeddings

Author(s): Duygu Ataman, Jose G. C. De Souza, Marco Turchi, Matteo Negri
Published in: Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), 2016, Page(s) 570-576
DOI: 10.18653/v1/S16-1086

Ten Years of WMT Evaluation Campaigns: Lessons Learnt

Author(s): Koehn, Philipp; Specia, Lucia; Haddow, Barry; Post, Matt; Bojar, Ondrej; Federmann, Christian
Published in: Proceedings of LREC 2016 Workshop Translation Evaluation: From Fragmented Tools and Data Sets to an Integrated Ecosystem, Portoroz, 2016. LREC 2016 Workshop Translation Evaluation: From Fragmented Tools and Data Sets to an Integrated Ecosystem, Portoroz, 2016., LREC 2016, Portorož, Slovenia, 2016-05-23 - 2016-05-28 , Issue 1, 2016

DFKI's system for WMT16 IT-domain task, including analysis of systematic errors

Author(s): Eleftherios Avramidis
Published in: Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers, 2016, Page(s) 415-422
DOI: 10.18653/v1/W16-2329

Manual and Automatic Paraphrases for MT Evaluation

Author(s): Barancıkova, Petra; Tamchyna, Ales
Published in: Proceedings of the 10th International Conference on Language Resources and Evaluation (LREC 2016) 10th International Conference on Language Resources and Evaluation (LREC 2016), LREC 2016, Portorož, Slovenia, 2016-05-23 - 2016-05-28 , Issue 2, 2016

Edinburgh's Statistical Machine Translation Systems for WMT16

Author(s): Philip Williams, Rico Sennrich, Maria Nadejde, Matthias Huck, Barry Haddow, Ondřej Bojar
Published in: Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers, 2016, Page(s) 399-410
DOI: 10.18653/v1/W16-2327

Alignment-Based Neural Machine Translation

Author(s): Tamer Alkhouli, Gabriel Bretschner, Jan-Thorsten Peter, Mohammed Hethnawi, Andreas Guta, Hermann Ney
Published in: Proceedings of the First Conference on Machine Translation: Volume 1, Research Papers, 2016, Page(s) 54-65
DOI: 10.18653/v1/W16-2206

Sheffield Systems for the English-Romanian WMT Translation Task

Author(s): Frédéric Blain, Xingyi Song, Lucia Specia
Published in: Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers, 2016, Page(s) 259-263
DOI: 10.18653/v1/W16-2307

The Karlsruhe Institute of Technology Systems for the News Translation Task in WMT 2016

Author(s): Thanh-Le Ha, Eunah Cho, Jan Niehues, Mohammed Mediani, Matthias Sperber, Alexandre Allauzen, Alexander Waibel
Published in: Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers, 2016, Page(s) 303-310
DOI: 10.18653/v1/W16-2314

SHEF-LIUM-NN: Sentence level Quality Estimation with Neural Network Features

Author(s): Kashif Shah, Fethi Bougares, Loïc Barrault, Lucia Specia
Published in: Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers, 2016, Page(s) 838-842
DOI: 10.18653/v1/W16-2392

Large-scale Multitask Learning for Machine Translation Quality Estimation

Author(s): Kashif Shah, Lucia Specia
Published in: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2016, Page(s) 558-567
DOI: 10.18653/v1/N16-1069

The QT21/HimL Combined Machine Translation System

Author(s): 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
Published in: Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers, 2016, Page(s) 344-355
DOI: 10.18653/v1/W16-2320

Achieving Accurate Conclusions in Evaluation of Automatic Machine Translation Metrics

Author(s): Yvette Graham, Qun Liu
Published in: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2016, Page(s) 1-10
DOI: 10.18653/v1/N16-1001

Tools and Guidelines for Principled Machine Translation Development

Author(s): Aranberri, Nora; Klejch, Ondrej; Popovic, Maja; Burchardt, Aljoscha; Avramidis, Eleftherios; Popel, Martin
Published in: Proceedings of the Tenth International Conference on Language Resources and Evaluation Tenth International Conference on Language Resources and Evaluation, LREC, Portorož, Slovenia , Issue 2, 2016

Using Factored Word Representation in Neural Network Language Models

Author(s): Jan Niehues, Thanh-Le Ha, Eunah Cho, Alex Waibel
Published in: Proceedings of the First Conference on Machine Translation: Volume 1, Research Papers, 2016, Page(s) 74-82
DOI: 10.18653/v1/W16-2208

SHEF-MIME: Word-level Quality Estimation Using Imitation Learning

Author(s): Daniel Beck, Andreas Vlachos, Gustavo Paetzold, Lucia Specia
Published in: Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers, 2016, Page(s) 772-776
DOI: 10.18653/v1/W16-2381

CUNI System for WMT16 Automatic Post-Editing and Multimodal Translation Tasks

Author(s): Jindřich Libovický, Jindřich Helcl, Marek Tlustý, Ondřej Bojar, Pavel Pecina
Published in: Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers, 2016, Page(s) 646-654
DOI: 10.18653/v1/W16-2361

Findings of the 2016 Conference on Machine Translation

Author(s): 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
Published in: Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers, 2016, Page(s) 131-198
DOI: 10.18653/v1/W16-2301

Towards a Systematic and Human-Informed Paradigm for High-Quality Machine Translation

Author(s): Burchardt, Aljoscha; Harris, Kim; Uszkoreit, Hans; Rehm, Georg
Published in: "Proceedings of the LREC Workshop ""Translation Evaluation –From Fragmented Tools and Data Sets to an Integrated Ecosystem” 10th edition of the Language Resources and Evaluation Conference - LREC Workshop ""Translation Evaluation –From Fragmented Tools and Data Sets to an Integrated Ecosystem”, LREC 2016, Portorož, Slovenia, 2016-05-23 - 2016-05-28 " , Issue 9, 2016

CharacTer: Translation Edit Rate on Character Level

Author(s): Weiyue Wang, Jan-Thorsten Peter, Hendrik Rosendahl, Hermann Ney
Published in: Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers, 2016, Page(s) 505-510
DOI: 10.18653/v1/W16-2342

LIMSI$@$WMT’16: Machine Translation of News

Author(s): Alexandre Allauzen, Lauriane Aufrant, Franck Burlot, Ophélie Lacroix, Elena Knyazeva, Thomas Lavergne, Guillaume Wisniewski, François Yvon
Published in: Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers, 2016, Page(s) 239-245
DOI: 10.18653/v1/W16-2304

Improving Neural Machine Translation Models with Monolingual Data

Author(s): Rico Sennrich, Barry Haddow, Alexandra Birch
Published in: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2016, Page(s) 86-96
DOI: 10.18653/v1/P16-1009

Frustratingly Easy Cross-Lingual Transfer for Transition-Based Dependency Parsing

Author(s): Ophélie Lacroix, Lauriane Aufrant, Guillaume Wisniewski, François Yvon
Published in: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2016, Page(s) 1058-1063
DOI: 10.18653/v1/N16-1121

Technology Landscape for Quality Evaluation: Combining the Needs of Research and Industry

Author(s): Burchardt, Aljoscha; Harris, Kim; Rehm, Georg; Specia, Lucia
Published in: "Proceedings of the LREC 2016 Workshop ""Translation Evaluation: From Fragmented Tools and Data Sets to an Integrated Ecosystem"" 10th edition of the Language Resources and Evaluation Conference - LREC Workshop ""Translation Evaluation –From Fragmented Tools and Data Sets to an Integrated Ecosystem”, Portorož, Slovenia, 2016-05-23 - 2016-05-28 " , Issue 9, 2016

PROTEST: A Test Suite for Evaluating Pronouns in Machine Translation

Author(s): Guillou, Liane; Hardmeier, Christian
Published in: Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016) Tenth International Conference on Language Resources and Evaluation (LREC 2016), LREC 2016, Portorož, Slovenia, 2016-05-23 - 2016-05-28 , Issue 2, 2016

A Comparative Study on Vocabulary Reduction for Phrase Table Smoothing

Author(s): Yunsu Kim, Andreas Guta, Joern Wuebker, Hermann Ney
Published in: Proceedings of the First Conference on Machine Translation: Volume 1, Research Papers, 2016, Page(s) 110-117
DOI: 10.18653/v1/W16-2212

ILLC-UvA Adaptation System (Scorpio) at WMT'16 IT-DOMAIN Task

Author(s): Hoang Cuong, Stella Frank, Khalil Sima'an
Published in: Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers, 2016, Page(s) 423-427
DOI: 10.18653/v1/W16-2330

Examining the Relationship between Preordering and Word Order Freedom in Machine Translation

Author(s): Joachim Daiber, Miloš Stanojević, Wilker Aziz, Khalil Sima'an
Published in: Proceedings of the First Conference on Machine Translation: Volume 1, Research Papers, 2016, Page(s) 118-130
DOI: 10.18653/v1/W16-2213

A Comparison between Count and Neural Network Models Based on Joint Translation and Reordering Sequences

Author(s): Andreas Guta, Tamer Alkhouli, Jan-Thorsten Peter, Joern Wuebker, Hermann Ney
Published in: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, 2015, Page(s) 1401-1411
DOI: 10.18653/v1/D15-1165

Cross-lingual Dependency Transfer : What Matters? Assessing the Impact of Pre- and Post-processing

Author(s): Ophélie Lacroix, Guillaume Wisniewski, François Yvon
Published in: Proceedings of the Workshop on Multilingual and Cross­-lingual Methods in NLP, 2016, Page(s) 20-29
DOI: 10.18653/v1/W16-1203

Graph-Based Translation Via Graph Segmentation

Author(s): Liangyou Li, Andy Way, Qun Liu
Published in: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2016, Page(s) 97-107
DOI: 10.18653/v1/P16-1010

Reference Bias in Monolingual Machine Translation Evaluation

Author(s): Marina Fomicheva, Lucia Specia
Published in: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 2016, Page(s) 77-82
DOI: 10.18653/v1/P16-2013

The FBK Participation in the WMT 2016 Automatic Post-editing Shared Task

Author(s): Rajen Chatterjee, José G. C. de Souza, Matteo Negri, Marco Turchi
Published in: Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers, 2016, Page(s) 745-750
DOI: 10.18653/v1/W16-2377

CobaltF: A Fluent Metric for MT Evaluation

Author(s): Marina Fomicheva, Núria Bel, Lucia Specia, Iria da Cunha, Anton Malinovskiy
Published in: Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers, 2016, Page(s) 483-490
DOI: 10.18653/v1/W16-2339

Scaling Up Word Clustering

Author(s): Jon Dehdari, Liling Tan, Josef van Genabith
Published in: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations, 2016, Page(s) 42-46
DOI: 10.18653/v1/N16-3009

Exploring the Planet of the APEs: a Comparative Study of State-of-the-art Methods for MT Automatic Post-Editing

Author(s): Rajen Chatterjee, Marion Weller, Matteo Negri, Marco Turchi
Published in: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), 2015, Page(s) 156-161
DOI: 10.3115/v1/P15-2026

Cross-lingual and Supervised Models for Morphosyntactic Annotation: a Comparison on Romanian

Author(s): Wisniewski, Guillaume; Aufrant, Lauriane; Yvon, Francois
Published in: Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016) Tenth International Conference on Language Resources and Evaluation (LREC 2016), LREC 2016, Portorož, Slovenia, 2016-05-23 - 2016-05-28 , Issue 3, 2016

Target-Side Context for Discriminative Models in Statistical Machine Translation

Author(s): Aleš Tamchyna, Alexander Fraser, Ondřej Bojar, Marcin Junczys-Dowmunt
Published in: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2016, Page(s) 1704-1714
DOI: 10.18653/v1/P16-1161

CzEng 1.6: Enlarged Czech-English Parallel Corpus with Processing Tools Dockered

Author(s): Kocmi, Tom; Popel, Martin; Variš, Dušan; Libovický, Jindřich; Novák, Michal; Bojar, Ondrej; Sudarikov, Roman; Dušek, Ondřej
Published in: Text, Speech, and Dialogue / Sojka, Petr (Editor) ; Cham : Springer International Publishing, 2016 19th International Conference on Text, Speech, and Dialogue, TSD 2016, Brno, Czech Republic , Issue 3, 2016

Online Multitask Learning for Machine Translation Quality Estimation

Author(s): José G. C. de Souza, Matteo Negri, Elisa Ricci, Marco Turchi
Published in: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), 2015, Page(s) 219-228
DOI: 10.3115/v1/P15-1022

Investigating Continuous Space Language Models for Machine Translation Quality Estimation

Author(s): Kashif Shah, Raymond W. M. Ng, Fethi Bougares, Lucia Specia
Published in: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, 2015, Page(s) 1073-1078
DOI: 10.18653/v1/D15-1125

Investigations on Phrase-based Decoding with Recurrent Neural Network Language and Translation Models

Author(s): Tamer Alkhouli, Felix Rietig, Hermann Ney
Published in: Proceedings of the Tenth Workshop on Statistical Machine Translation, 2015, Page(s) 294-303
DOI: 10.18653/v1/W15-3034

SHEF-NN: Translation Quality Estimation with Neural Networks

Author(s): Kashif Shah, Varvara Logacheva, Gustavo Paetzold, Frédéric Blain, Daniel Beck, Fethi Bougares, Lucia Specia
Published in: Proceedings of the Tenth Workshop on Statistical Machine Translation, 2015, Page(s) 342-347
DOI: 10.18653/v1/W15-3041

Findings of the 2015 Workshop on Statistical Machine Translation

Author(s): Ondřej Bojar, Rajen Chatterjee, Christian Federmann, Barry Haddow, Matthias Huck, Chris Hokamp, Philipp Koehn, Varvara Logacheva, Christof Monz, Matteo Negri, Matt Post, Carolina Scarton, Lucia Specia, Marco Turchi
Published in: Proceedings of the Tenth Workshop on Statistical Machine Translation, 2015, Page(s) 1-46
DOI: 10.18653/v1/W15-3001

What a Transfer-Based System Brings to the Combination with PBMT

Author(s): Aleš Tamchyna, Ondrej Bojar
Published in: Proceedings of the Fourth Workshop on Hybrid Approaches to Translation (HyTra), 2015, Page(s) 11-20
DOI: 10.18653/v1/W15-4103

The Karlsruhe Institute of Technology Translation Systems for the WMT 2015

Author(s): Eunah Cho, Thanh-Le Ha, Jan Niehues, Teresa Herrmann, Mohammed Mediani, Yuqi Zhang, Alex Waibel
Published in: Proceedings of the Tenth Workshop on Statistical Machine Translation, 2015, Page(s) 92-97
DOI: 10.18653/v1/W15-3008

LIMSI$@$WMT'15 : Translation Task

Author(s): Benjamin Marie, Alexandre Allauzen, Franck Burlot, Quoc-Khanh Do, Julia Ive, elena knyazeva, Matthieu Labeau, Thomas Lavergne, Kevin Löser, Nicolas Pécheux, François Yvon
Published in: Proceedings of the Tenth Workshop on Statistical Machine Translation, 2015, Page(s) 145-151
DOI: 10.18653/v1/W15-3016

ListNet-based MT Rescoring

Author(s): Jan Niehues, Quoc-Khanh DO, Alexandre Allauzen, Alex Waibel
Published in: Proceedings of the Tenth Workshop on Statistical Machine Translation, 2015, Page(s) 248-255
DOI: 10.18653/v1/W15-3030

BEER 1.1: ILLC UvA submission to metrics and tuning task

Author(s): Miloš Stanojević, Khalil Sima'an
Published in: Proceedings of the Tenth Workshop on Statistical Machine Translation, 2015, Page(s) 396-401
DOI: 10.18653/v1/W15-3050

CASICT-DCU Participation in WMT2015 Metrics Task

Author(s): Hui Yu, Qingsong Ma, Xiaofeng Wu, Qun Liu
Published in: Proceedings of the Tenth Workshop on Statistical Machine Translation, 2015, Page(s) 417-421
DOI: 10.18653/v1/W15-3053

The KIT-LIMSI Translation System for WMT 2015

Author(s): Thanh-Le Ha, Quoc-Khanh DO, Eunah Cho, Jan Niehues, Alexandre Allauzen, François Yvon, Alex Waibel
Published in: Proceedings of the Tenth Workshop on Statistical Machine Translation, 2015, Page(s) 120-125
DOI: 10.18653/v1/W15-3012

Extended Translation Models in Phrase-based Decoding

Author(s): Andreas Guta, Joern Wuebker, Miguel Graca, Yunsu Kim, Hermann Ney
Published in: Proceedings of the Tenth Workshop on Statistical Machine Translation, 2015, Page(s) 282-293
DOI: 10.18653/v1/W15-3033

Automatic Post-Editing for the DiscoMT Pronoun Translation Task

Author(s): Liane Guillou
Published in: Proceedings of the Second Workshop on Discourse in Machine Translation, 2015, Page(s) 65-71
DOI: 10.18653/v1/W15-2509

Analysing ParCor and its Translations by State-of-the-art SMT Systems

Author(s): Liane Guillou, Bonnie Webber
Published in: Proceedings of the Second Workshop on Discourse in Machine Translation, 2015, Page(s) 24-32
DOI: 10.18653/v1/W15-2503

Results of the WMT15 Metrics Shared Task

Author(s): Miloš Stanojević, Amir Kamran, Philipp Koehn, Ondřej Bojar
Published in: Proceedings of the Tenth Workshop on Statistical Machine Translation, 2015, Page(s) 256-273
DOI: 10.18653/v1/W15-3031

Reordering Grammar Induction

Author(s): Miloš Stanojević, Khalil Sima'an
Published in: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, 2015, Page(s) 44-54
DOI: 10.18653/v1/D15-1005

Results of the WMT15 Tuning Shared Task

Author(s): Miloš Stanojević, Amir Kamran, Ondřej Bojar
Published in: Proceedings of the Tenth Workshop on Statistical Machine Translation, 2015, Page(s) 274-281
DOI: 10.18653/v1/W15-3032

Edinburgh's Syntax-Based Systems at WMT 2015

Author(s): Philip Williams, Rico Sennrich, Maria Nadejde, Matthias Huck, Philipp Koehn
Published in: Proceedings of the Tenth Workshop on Statistical Machine Translation, 2015, Page(s) 199-209
DOI: 10.18653/v1/W15-3024

MT Quality Estimation for Computer-assisted Translation: Does it Really Help?

Author(s): Marco Turchi, Matteo Negri, Marcello Federico
Published in: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), 2015, Page(s) 530-535
DOI: 10.3115/v1/P15-2087

The FBK Participation in the WMT15 Automatic Post-editing Shared Task

Author(s): Rajen Chatterjee, Marco Turchi, Matteo Negri
Published in: Proceedings of the Tenth Workshop on Statistical Machine Translation, 2015, Page(s) 210-215
DOI: 10.18653/v1/W15-3025

A Joint Dependency Model of Morphological and Syntactic Structure for Statistical Machine Translation

Author(s): Rico Sennrich, Barry Haddow
Published in: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, 2015, Page(s) 2081-2087
DOI: 10.18653/v1/D15-1248

UPF-Cobalt Submission to WMT15 Metrics Task

Author(s): Marina Fomicheva, Núria Bel, Iria da Cunha, Anton Malinovskiy
Published in: Proceedings of the Tenth Workshop on Statistical Machine Translation, 2015, Page(s) 373-379
DOI: 10.18653/v1/W15-3046

Multi-level Translation Quality Prediction with QuEst++

Author(s): Lucia Specia, Gustavo Paetzold, Carolina Scarton
Published in: Proceedings of ACL-IJCNLP 2015 System Demonstrations, 2015, Page(s) 115-120
DOI: 10.3115/v1/P15-4020

Splitting Compounds by Semantic Analogy

Author(s): Quirozy, Lautaro; Frank, Stella; Daiber, Joachim; Wechsler, Roger
Published in: Proceedings of the 1st Deep Machine Translation Workshop (DMTW 2015) Deep Machine Translation Workshop - DMTW 2015, DMTW 2015, Praha, Czech Republic, 2015-09-03 - 2015-09-04 , Issue 2, 2015

Stripping Adjectives: Integration Techniques for Selective Stemming in SMT Systems

Author(s): Waibel, Alex; Niehues, Jan; Slawik, Isabel
Published in: Proceedings of the 18th Annual Conference of the European Association for Machine Translation (EAMT 2015) 18th Annual Conference of the European Association for Machine Translation (EAMT 2015), EAMT 2015, Antalya, Turkey, 2015-05-11 - 2015-05-13 , Issue 3, 2015

Results of the WMT16 Tuning Shared Task

Author(s): Bojar, Ondřej; Jawaid, Bushra; Kamran, Amir; Stanojević, Miloš
Published in: Proceedings ACL 2016, Issue 23, 2016

Evaluating MT systems with BEER

Author(s): Miloš Stanojević, Khalil Sima’an
Published in: The Prague Bulletin of Mathematical Linguistics, Issue 104/1, 2015, ISSN 1804-0462
DOI: 10.1515/pralin-2015-0010

Machine translation quality in an audiovisual context

Author(s): Aljoscha Burchardt, Arle Lommel, Lindsay Bywood, Kim Harris, Maja Popović
Published in: Target, Issue 28/2, 2016, Page(s) 206-221, ISSN 0924-1884
DOI: 10.1075/target.28.2.03bur

Towards Optimizing MT for Post-Editing Effort: Can BLEU Still Be Useful?

Author(s): Mikel L. Forcada, Felipe Sánchez-Martínez, Miquel Esplà-Gomis, Lucia Specia
Published in: The Prague Bulletin of Mathematical Linguistics, Issue 108/1, 2017, ISSN 1804-0462
DOI: 10.1515/pralin-2017-0019

Visualizing Neural Machine Translation Attention and Confidence

Author(s): Matīss Rikters, Mark Fishel, Ondřej Bojar
Published in: The Prague Bulletin of Mathematical Linguistics, Issue 109/1, 2017, ISSN 1804-0462
DOI: 10.1515/pralin-2017-0037

Learning Morphological Normalization for Translation from and into Morphologically Rich Languages

Author(s): Franck Burlot, François Yvon
Published in: The Prague Bulletin of Mathematical Linguistics, Issue 108/1, 2017, ISSN 1804-0462
DOI: 10.1515/pralin-2017-0008

A Bayesian non-linear method for feature selection in machine translation quality estimation

Author(s): Kashif Shah, Trevor Cohn, Lucia Specia
Published in: Machine Translation, Issue 29/2, 2015, Page(s) 101-125, ISSN 0922-6567
DOI: 10.1007/s10590-014-9164-x

TmTriangulate: A Tool for Phrase Table Triangulation

Author(s): Duc Tam Hoang, Ondřej Bojar
Published in: The Prague Bulletin of Mathematical Linguistics, Issue 104/1, 2015, ISSN 1804-0462
DOI: 10.1515/pralin-2015-0015

Sampling Phrase Tables for the Moses Statistical Machine Translation System

Author(s): Ulrich Germann
Published in: The Prague Bulletin of Mathematical Linguistics, Issue 104/1, 2015, ISSN 1804-0462
DOI: 10.1515/pralin-2015-0012

CsEnVi Pairwise Parallel Corpora

Author(s): Hoang, Tam; Bojar, Ondřej
Published in: Issue 2, 2015