Global Under-Resourced MEedia Translation

Project Information

GoURMET

Grant agreement ID: 825299

DOI 10.3030/825299

Project closed

EC signature date 25 October 2018

Start date 1 January 2019

End date 30 June 2022

Funded under

• INDUSTRIAL LEADERSHIP - Leadership in enabling and industrial technologies - Information and Communication Technologies (ICT)

Total cost € 2 906 098,75

EU contribution € 2 906 098,75

Coordinated by

THE UNIVERSITY OF EDINBURGH
United Kingdom

Deliverables

Documents, reports (18)

Initial progress report on integration
Final Dissemination and Exploitation Report
Final progress report on data gathering and augmentation
Initial progress report on data gathering and augmentation
Initial progress report on learning structural models
Final report on modelling morphological structure
Interim Dissemination and Exploitation Report
Final report on transfer learning
Survey of relevant low-resource languages
Final progress report on integration
Final progress report on evaluation
Internal progress and planning report
Initial progress report on evaluation
Final report on learning structural models
Use Case Description and Requirements
Evaluation Plan
Initial progress report on transfer learning
Initial progress report on modelling morphological structure

Websites, patent fillings, videos etc. (2)

Project web portal
Project fact sheet

Open Research Data Pilot (3)

Final release of project data
Data Management Plan
Initial release of project data

Publications

Conference proceedings (58)

Language Modeling, Lexical Translation, Reordering: The Training Process of NMT through the Lens of Classical SMT

Author(s): Voita, Elena; Sennrich, Rico; Titov, Ivan
Published in: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021, Page(s) 8478–8491
Publisher: Association for Computational Linguistics
DOI: 10.5167/uzh-208888

Document-level Neural MT: A Systematic Comparison

Author(s): António Lopes; Amin Farajian, M.; Rachel Bawden; Michael Zhang; André Martins
Published in: Proceedings of the 22nd Annual Conference of the European Association for Machine Translation, 2020, Page(s) 225–234
Publisher: European Association for Machine Translation

Rethinking Data Augmentation for Low-Resource Neural Machine Translation: A Multi-Task Learning Approach

Author(s): Sánchez-Cartagena, Víctor M.; Esplà-Gomis, Miquel; Pérez-Ortiz, Juan Antonio; Sánchez-Martínez, Felipe
Published in: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021, Page(s) 8502–8516
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2021.emnlp-main.669

Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translation

Author(s): Eikema, B.; Aziz, W.; Scott, D.; Bel, N.; Zong, C.
Published in: Proceedings of the 28th International Conference on Computational Linguistics, 2020, Page(s) 4506–4520
Publisher: International Committee on Computational Linguistics
DOI: 10.18653/v1/2020.coling-main.398

The University of Edinburgh's English-German and English-Hausa Submissions to the WMT21 News Translation Task

Author(s): Chen; Helcl; Germann; Burchell; Bogoychev; Miceli Barone; Waldendorf; Birch; Heafield
Published in: Proceedings of the Sixth Conference on Machine Translation, 2021, Page(s) 104–109
Publisher: Association for Computational Linguistics
DOI: 10.5281/zenodo.6672728

Latent Transformations for Discrete-Data Normalising Flows

Author(s): Hesselink, Rob; Aziz, Wilker
Published in: Issue 1, 2020
Publisher: Informal
DOI: 10.48550/arxiv.2006.06346

Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity

Author(s): Correia, G. M.; Niculae, V.; Aziz, W.; Martins, A. F. T.
Published in: Scopus - Elsevier, Issue 1, 2020
Publisher: Advances in Neural Information Processing Systems 33
DOI: 10.48550/arxiv.2007.01919

Non-Autoregressive Machine Translation: It's Not as Fast as it Seems

Author(s): Helcl; Haddow; Birch
Published in: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2022
Publisher: Association for Computational Linguistics
DOI: 10.5281/zenodo.6672770

Bridging linguistic typology and multilingual machine translation with multi-view language representations

Author(s): Arturo Oncevay; Barry Haddow; Alexandra Birch
Published in: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020, Page(s) 2391–2406
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2020.emnlp-main.187

Block Neural Autoregressive Flow

Author(s): De Cao, Nicola; Titov, Ivan; Aziz, Wilker
Published in: Issue 1, 2020
Publisher: PMLR
DOI: 10.48550/arxiv.1904.04676

The University of Edinburgh's English-Tamil and English-Inuktitut Submissions to the WMT20 News Translation Task

Author(s): Bawden; Birch; Dobreva; Oncevay; Miceli; Williams
Published in: Proceedings of the Fifth Conference on Machine Translation, 2020, Page(s) 92–99
Publisher: Association for Computational Linguistics
DOI: 10.5281/zenodo.6672692

How do Decisions Emerge across Layers in Neural Models? Interpretation with Differentiable Masking

Author(s): De Cao, N.; Schlichtkrull, M.; Aziz, W.; Titov, I.; Webber, B.; Cohn, T.; He, Y.; Liu, Y.
Published in: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020, Page(s) 3243–3255
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2020.emnlp-main.262

Sampling-Based Minimum Bayes Risk Decoding for Neural Machine Translation

Author(s): Eikema, Bryan; Aziz, Wilker
Published in: Issue 3, 2020
Publisher: CoRR
DOI: 10.48550/arxiv.2108.04718

Few-shot learning through contextual data augmentation

Author(s): Farid Arthaud; Rachel Bawden; Alexandra Birch
Published in: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, 2021, Page(s) 1049–1062
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2021.eacl-main.90

Exploring Diversity in Back Translation for Low-Resource Machine Translation

Author(s): Burchell; Birch; Heafield
Published in: Workshop on Deep Learning for Low-Resource NLP, NAACL, 2022
Publisher: Association for Computational Linguistics
DOI: 10.5281/zenodo.6672772

The University of Edinburgh-Uppsala University’s Submission to the WMT 2020 Chat Translation Task

Author(s): Nikita Moghe; Christian Hardmeier; Rachel Bawden
Published in: Proceedings of the Fifth Conference on Machine Translation, 2020, Page(s) 473–478
Publisher: Association for Computational Linguistics

A Study in Improving BLEU Reference Coverage with Diverse Automatic Paraphrasing

Author(s): Rachel Bawden; Biao Zhang; Lisa Yankovskaya; Andre Tättar; Matt Post
Published in: Findings of the Association for Computational Linguistics: EMNLP 2020, 2020, Page(s) 918–932
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2020.findings-emnlp.82

Quantifying Synthesis and Fusion and their Impact on Machine Translation

Author(s): Oncevay; Ataman; Haddow; Birch; Bjerva
Published in: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2022
Publisher: Association for Computational Linguistics
DOI: 10.5281/zenodo.6672763

Exploring Unsupervised Pretraining Objectives for Machine Translation

Author(s): Baziotis; Titov; Birch; Haddow
Published in: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, 2021, Page(s) 2956–2971
Publisher: Association for Computational Linguistics
DOI: 10.5281/zenodo.6672712

Understanding the effects of word-level linguistic annotations in under-resourced neural machine translation

Author(s): Víctor M. Sánchez-Cartagena; Juan Antonio Pérez-Ortiz; Felipe Sánchez-Martínez
Published in: Proceedings of the 28th International Conference on Computational Linguistics, 2020, Page(s) 3938–3950
Publisher: International Committee on Computational Linguistics
DOI: 10.18653/v1/2020.coling-main.349

Sparse Communication via Mixed Distributions

Author(s): Farinhas, António; Aziz, Wilker; Niculae, Vlad; Martins, André F. T.
Published in: Issue 1, 2022
Publisher: ICLR
DOI: 10.48550/arxiv.2108.02658

Efficient marginalization of discrete and structured latent variables via sparsity

Author(s): Correia, Gonçalo M.; Niculae, Vlad; Aziz, Wilker; Martins, André F. T.
Published in: Advances in Neural Information Processing Systems, 2020, Page(s) 11789-11802
Publisher: Curran Associates, Inc.

ParBLEU: Augmenting Metrics with Automatic Paraphrases for the WMT'20 Metrics Shared Task

Author(s): Bawden, Rachel; Zhang, Biao; Tättar, Andre; Post, Matt
Published in: Proceedings of the Fifth Conference on Machine Translation, 2020, Page(s) 887–894
Publisher: Association for Computational Linguistics

Cross-lingual Intermediate Fine-tuning improves Dialogue State Tracking

Author(s): Moghe; Steedman; Birch
Published in: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021, Page(s) 1137–1150
Publisher: Association for Computational Linguistics
DOI: 10.5281/zenodo.6672775

Widening the Representation Bottleneck in Neural Machine Translation with Lexical Shortcuts

Author(s): Denis Emelin, Ivan Titov, Rico Sennrich
Published in: Proceedings of the Fourth Conference on Machine Translation (Volume 1: Research Papers), 2019, Page(s) 102-115
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/w19-5211

Document Sub-structure in Neural Machine Translation

Author(s): Dobreva, Radina; Zhou, Jie; Bawden, Rachel
Published in: Proceeding of the 12th Language Resources and Evaluation Conference, 2020, Page(s) 3657--3667, ISBN 979-10-95546-34-4
Publisher: European Language Resources Association
DOI: 10.5281/zenodo.3923463

MultiWord Expression Aware Neural Machine Translation

Author(s): Zaninello, Andrea; Birch, Alexandra
Published in: Proceedings of The 12th Language Resources and Evaluation Conference, 2020, Page(s) 3816-3825, ISBN 979-10-95546-34-4
Publisher: European Language Resources Association
DOI: 10.5281/zenodo.3923509

The University of Edinburgh’s Submissions to the WMT19 News Translation Task

Author(s): Rachel Bawden, Nikolay Bogoychev, Ulrich Germann, Roman Grundkiewicz, Faheem Kirefu, Antonio Valerio Miceli Barone, Alexandra Birch
Published in: Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), 2019, Page(s) 103-115
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/w19-5304

Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation

Author(s): Biao Zhang, Philip Williams, Ivan Titov, Rico Sennrich
Published in: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020, Page(s) 1628-1639
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2020.acl-main.148

Interpretable Neural Predictions with Differentiable Binary Variables

Author(s): Joost Bastings, Wilker Aziz, Ivan Titov
Published in: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019, Page(s) 2963-2977
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/p19-1284

Auto-Encoding Variational Neural Machine Translation

Author(s): Bryan Eikema, Wilker Aziz
Published in: Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019), Issue Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019), 2019, Page(s) 124-141
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/w19-4315

Effective Estimation of Deep Generative Language Models

Author(s): Tom Pelsmaeker, Wilker Aziz
Published in: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020, Page(s) 7220-7236
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2020.acl-main.646

Block Neural Autoregressive Flow

Author(s): De Cao, Nicola; Titov, Ivan; Aziz, Wilker
Published in: Proceedings of the Thirty-Fifth Conference on Uncertainty in Artificial Intelligence, UAI 2019, 2019, Page(s) 15
Publisher: Association for Uncertainty in Artificial Intelligence

On the Importance of Word Boundaries in Character-level Neural Machine Translation

Author(s): Duygu Ataman, Orhan Firat, Mattia A. Di Gangi, Marcello Federico, Alexandra Birch
Published in: Proceedings of the 3rd Workshop on Neural Generation and Translation, 2019, Page(s) 187-193
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/D19-5619

A Latent Morphology Model for Open-Vocabulary Neural Machine Translation

Author(s): Ataman, Duygu; Aziz, Wilker; Birch, Alexandra
Published in: Proceedings of the International Conference on Learning Representations 2020, 2020
Publisher: International Conference on Learning Representations

Findings of the 2019 Conference on Machine Translation (WMT19)

Author(s): Loïc Barrault, Ondřej Bojar, Marta R. Costa-jussà, Christian Federmann, Mark Fishel, Yvette Graham, Barry Haddow, Matthias Huck, Philipp Koehn, Shervin Malmasi, Christof Monz, Mathias Müller, Santanu Pal, Matt Post, Marcos Zampieri
Published in: Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), 2019, Page(s) 1-61
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/w19-5301

Estimating post-editing effort: a study on human judgements, task-based and reference-based metrics of MT quality

Author(s): Scarton, Scarton; Forcada, Mikel L.; Esplà-Gomis, Miquel; Specia, Lucia
Published in: Proceedings of the 16th International Workshop on Spoken Language Translation 2019, Issue 10, 2019
Publisher: International Workshop on Spoken Language Translation
DOI: 10.5281/zenodo.3923606

An English-Swahili parallel corpus and its use for neural machine translation in the news domain

Author(s): Sánchez-Martínez, Felipe; Sánchez-Cartagena, Víctor M.; Pérez-Ortiz, Juan Antonio; Forcada, Mikel L.; Esplà-Gomis, Miquel; Secker, Andrew; Coleman, Susie; Wall, Julie
Published in: Proceedings of the 22nd Annual Conference of the European Association for Machine Translation, 2020, Page(s) 299–308
Publisher: European Association for Machine Translation
DOI: 10.5281/zenodo.3923590

Towards Making the Most of Context in Neural Machine Translation

Author(s): Zaixiang Zheng, Xiang Yue, Shujian Huang, Jiajun Chen, Alexandra Birch
Published in: Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, 2020, Page(s) 3983-3989, ISBN 978-0-9992411-6-5
Publisher: International Joint Conferences on Artificial Intelligence Organization
DOI: 10.24963/ijcai.2020/551

Towards a Multi-view Language Representation: A Shared Space of Discrete and Continuous Language Features

Author(s): Oncevay, Arturo; Haddow, Barry; Birch, Alexandra
Published in: Proceedings of TyP-NLP: The First Workshop on Typology for Polyglot NLP, 2019
Publisher: Association for Computational Linguistics
DOI: 10.5281/zenodo.3923625

Architecture of a Scalable, Secure and Resilient Translation Platform for Multilingual News Media

Author(s): Coleman, Susie; Secker, Andrew; Bawden, Rachel; Haddow, Barry; Birch, Alexandra
Published in: Proceedings of the 1st International Workshop on Language Technology Platforms, 2020, Page(s) 16–21
Publisher: European Language Resources Association
DOI: 10.5281/zenodo.3923492

The Universitat d’Alacant Submissions to the English-to-Kazakh News Translation Task at WMT 2019

Author(s): Víctor M. Sánchez-Cartagena, Juan Antonio Pérez-Ortiz, Felipe Sánchez-Martínez
Published in: Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), 2019, Page(s) 356-363
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/w19-5339

A multi-source approach for Breton–French hybrid machine translation

Author(s): Sánchez-Cartagena, Víctor M.; Forcada, Mikel L.; Sánchez-Martínez, Felipe
Published in: Proceedings of the 22nd Annual Conference of the European Association for Machine Translation, 2020, Page(s) 61–70
Publisher: European Association for Machine Translation
DOI: 10.5281/zenodo.3923596

Global Under-Resourced Media Translation (GoURMET)

Author(s): Alexandra Birch, Barry Haddow, Ivan Tito, Antonio Valerio Miceli Barone, Rachel Bawden, Felipe Sánchez-Martínez, Mikel L. Forcada, Miquel Esplà-Gomis, Víctor Sánchez-Cartagena, Juan Antonio Pérez-Ortiz, Wilker Aziz, Andrew Secker, Peggy van der Kreeft
Published in: Proceedings of Machine Translation Summit XVII Volume 2: Translator, Project and User Tracks, 2019, Page(s) 122–122
Publisher: European Association for Machine Translation

Highly Parallel Autoregressive Entity Linking with Discriminative Correction

Author(s): De Cao, Nicola; Aziz, Wilker; Titov, Ivan
Published in: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021, Page(s) 7662–7669
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2021.emnlp-main.604

Distributionally Robust Recurrent Decoders with Random Network Distillation

Author(s): Miceli Barone; Birch; Sennrich
Published in: Proceedings of the 7th Workshop on Representation Learning for NLP, 2022, Page(s) 1–8
Publisher: Association for Computational Linguistics
DOI: 10.5281/zenodo.6672752

On Sparsifying Encoder Outputs in Sequence-to-Sequence Models

Author(s): Biao Zhang; Ivan Titov; Rico Sennrich
Published in: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, 2021, Page(s) 2888–2900
Publisher: Association for Computational Linguistics
DOI: 10.5167/uzh-208878

Exploring Unsupervised Pretraining Objectives for Machine Translation

Author(s): Christos Baziotis; Ivan Titov; Alexandra Birch; Barry Haddow
Published in: Issue 1, 2021
Publisher: ACL
DOI: 10.48550/arxiv.2106.05634

Towards Machine Translation for the Kurdish Language

Author(s): Ahmadi, Sina; Masoud, Mariam
Published in: Proceedings of the 3rd Workshop on Technologies for MT of Low Resource Languages, 2020, Page(s) 87–98
Publisher: Association for Computational Linguistics

Non-Autoregressive Machine Translation: It's Not as Fast as it Seems

Author(s): Helcl; Haddow; Birch
Published in: EMNLP, Issue 5, 2022
Publisher: ACL
DOI: 10.5281/zenodo.6672769

Bicleaner at WMT 2020: Universitat d'Alacant-Prompsit's submission to the parallel corpus filtering shared task

Author(s): Espla-Gomis; Sanchez-Cartagena; Zaragoza-Bernabeu; Sanchez-Martinez
Published in: Proceedings of the Fifth Conference on Machine Translation, 2020, Page(s) 952–958
Publisher: Association for Computational Linguistics
DOI: 10.5281/zenodo.6672700

Surprise Language Challenge: Developing a Neural Machine Translation System between Pashto and English in Two Months

Author(s): Alexandra Birch; Barry Haddow; Antonio Valerio Miceli Barone; Jindrich Helcl; Jonas Waldendorf; Felipe Sánchez Martínez; Mikel Forcada; Víctor Sánchez Cartagena; Juan Antonio Pérez-Ortiz; Miquel Esplà-Gomis; Wilker Aziz; Lina Murady; Sevi Sariisik; Peggy van der Kreeft; Kay Macquarrie
Published in: Proceedings of Machine Translation Summit XVIII: Research Track, 2021, Page(s) 92–102
Publisher: Association for Machine Translation in the Americas
DOI: 10.5281/zenodo.6580252

Cross-lingual Intermediate Fine-tuning improves Dialogue State Tracking

Author(s): Moghe; Steedman; Birch
Published in: Issue 3, 2021
Publisher: ACL
DOI: 10.5281/zenodo.6672774

Language Model Prior for Low-Resource Neural Machine Translation

Author(s): Christos Baziotis; Barry Haddow; Alexandra Birch
Published in: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020, Page(s) 7622–7634
Publisher: Association for Computational Linguistics
DOI: 10.18653/v1/2020.emnlp-main.615

The University of Edinburgh's Submissions to the WMT19 News Translation Task

Author(s): Bawden, Rachel; Bogoychev, Nikolay; Germann, Ulrich; Grundkiewicz, Roman; Kirefu, Faheem; Miceli Barone, Antonio Valerio; Birch, Alexandra
Published in: Issue 1, 2019
Publisher: ACL
DOI: 10.48550/arxiv.1907.05854

The University of Edinburgh's Submissions to the WMT19 News Translation Task

Author(s): Bawden, Rachel; Bogoychev, Nikolay; Germann, Ulrich; Grundkiewicz, Roman; Kirefu, Faheem; Miceli Barone, Antonio Valerio; Birch, Alexandra
Published in: Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), 2019, Page(s) 103–115
Publisher: Association for Computational Linguistics

Towards Machine Translation for the Kurdish Language

Author(s): Ahmadi, Sina; Masoud, Mariam
Published in: Issue 3, 2020
Publisher: ACL
DOI: 10.48550/arxiv.2010.06041

Distributionally Robust Recurrent Decoders with Random Network Distillation

Author(s): Miceli-Barone, Antonio Valerio; Birch, Alexandra; Sennrich, Rico
Published in: Issue 1, 2022
Publisher: ACL
DOI: 10.5281/zenodo.6672751

Other (6)

Sampling-Based Minimum Bayes Risk Decoding for Neural Machine Translation

Author(s): Eikema, Bryan; Aziz, Wilker
Published in: 2021
Publisher: arxiv.org

PMIndia -- A Collection of Parallel Corpora of Languages of India

Author(s): Haddow, Barry; Kirefu, Faheem
Published in: 2020
Publisher: arxiv.org

Sparse Communication via Mixed Distributions

Author(s): Farinhas, António; Aziz, Wilker; Niculae, Vlad; Martins, André F. T.
Published in: 2021
Publisher: arxiv.org

Block Neural Autoregressive Flow

Author(s): De Cao, Nicola; Titov, Ivan; Aziz, Wilker
Published in: 2019
Publisher: arxiv.org

Revisiting Neural Language Modelling with Syllables

Author(s): Oncevay, Arturo; Rojas, Kervy Rivas
Published in: 2020
Publisher: arxiv.org

Latent Transformations for Discrete-Data Normalising Flows

Author(s): Hesselink, Rob; Aziz, Wilker
Published in: 2020
Publisher: arxiv.org

Peer reviewed articles (1)

Survey of Low-Resource Machine Translation

Author(s): Haddow; Bawden; Miceli Barone; Helcl; Birch
Published in: Computational Linguistics, 2022, ISSN 0891-2017
Publisher: MIT Press
DOI: 10.5281/zenodo.6672725