Global Under-Resourced MEedia Translation

Rezultaty

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

Project web portal
Project fact sheet

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

Publikacje

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

Autorzy: Voita, Elena; Sennrich, Rico; Titov, Ivan
Opublikowane w: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021, Strona(/y) 8478–8491
Wydawca: Association for Computational Linguistics
DOI: 10.5167/uzh-208888

Document-level Neural MT: A Systematic Comparison

Autorzy: António Lopes; Amin Farajian, M.; Rachel Bawden; Michael Zhang; André Martins
Opublikowane w: Proceedings of the 22nd Annual Conference of the European Association for Machine Translation, 2020, Strona(/y) 225–234
Wydawca: European Association for Machine Translation

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

Autorzy: Sánchez-Cartagena, Víctor M.; Esplà-Gomis, Miquel; Pérez-Ortiz, Juan Antonio; Sánchez-Martínez, Felipe
Opublikowane w: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021, Strona(/y) 8502–8516
Wydawca: 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

Autorzy: Eikema, B.; Aziz, W.; Scott, D.; Bel, N.; Zong, C.
Opublikowane w: Proceedings of the 28th International Conference on Computational Linguistics, 2020, Strona(/y) 4506–4520
Wydawca: 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

Autorzy: Chen; Helcl; Germann; Burchell; Bogoychev; Miceli Barone; Waldendorf; Birch; Heafield
Opublikowane w: Proceedings of the Sixth Conference on Machine Translation, 2021, Strona(/y) 104–109
Wydawca: Association for Computational Linguistics
DOI: 10.5281/zenodo.6672728

Latent Transformations for Discrete-Data Normalising Flows

Autorzy: Hesselink, Rob; Aziz, Wilker
Opublikowane w: Numer 1, 2020
Wydawca: Informal
DOI: 10.48550/arxiv.2006.06346

Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity

Autorzy: Correia, G. M.; Niculae, V.; Aziz, W.; Martins, A. F. T.
Opublikowane w: Scopus - Elsevier, Numer 1, 2020
Wydawca: 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

Autorzy: Helcl; Haddow; Birch
Opublikowane w: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2022
Wydawca: Association for Computational Linguistics
DOI: 10.5281/zenodo.6672770

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

Autorzy: Arturo Oncevay; Barry Haddow; Alexandra Birch
Opublikowane w: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020, Strona(/y) 2391–2406
Wydawca: Association for Computational Linguistics
DOI: 10.18653/v1/2020.emnlp-main.187

Block Neural Autoregressive Flow

Autorzy: De Cao, Nicola; Titov, Ivan; Aziz, Wilker
Opublikowane w: Numer 1, 2020
Wydawca: PMLR
DOI: 10.48550/arxiv.1904.04676

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

Autorzy: Bawden; Birch; Dobreva; Oncevay; Miceli; Williams
Opublikowane w: Proceedings of the Fifth Conference on Machine Translation, 2020, Strona(/y) 92–99
Wydawca: Association for Computational Linguistics
DOI: 10.5281/zenodo.6672692

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

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

Sampling-Based Minimum Bayes Risk Decoding for Neural Machine Translation

Autorzy: Eikema, Bryan; Aziz, Wilker
Opublikowane w: Numer 3, 2020
Wydawca: CoRR
DOI: 10.48550/arxiv.2108.04718

Few-shot learning through contextual data augmentation

Autorzy: Farid Arthaud; Rachel Bawden; Alexandra Birch
Opublikowane w: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, 2021, Strona(/y) 1049–1062
Wydawca: Association for Computational Linguistics
DOI: 10.18653/v1/2021.eacl-main.90

Exploring Diversity in Back Translation for Low-Resource Machine Translation

Autorzy: Burchell; Birch; Heafield
Opublikowane w: Workshop on Deep Learning for Low-Resource NLP, NAACL, 2022
Wydawca: Association for Computational Linguistics
DOI: 10.5281/zenodo.6672772

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

Autorzy: Nikita Moghe; Christian Hardmeier; Rachel Bawden
Opublikowane w: Proceedings of the Fifth Conference on Machine Translation, 2020, Strona(/y) 473–478
Wydawca: Association for Computational Linguistics

A Study in Improving BLEU Reference Coverage with Diverse Automatic Paraphrasing

Autorzy: Rachel Bawden; Biao Zhang; Lisa Yankovskaya; Andre Tättar; Matt Post
Opublikowane w: Findings of the Association for Computational Linguistics: EMNLP 2020, 2020, Strona(/y) 918–932
Wydawca: Association for Computational Linguistics
DOI: 10.18653/v1/2020.findings-emnlp.82

Quantifying Synthesis and Fusion and their Impact on Machine Translation

Autorzy: Oncevay; Ataman; Haddow; Birch; Bjerva
Opublikowane w: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2022
Wydawca: Association for Computational Linguistics
DOI: 10.5281/zenodo.6672763

Exploring Unsupervised Pretraining Objectives for Machine Translation

Autorzy: Baziotis; Titov; Birch; Haddow
Opublikowane w: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, 2021, Strona(/y) 2956–2971
Wydawca: Association for Computational Linguistics
DOI: 10.5281/zenodo.6672712

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

Autorzy: Víctor M. Sánchez-Cartagena; Juan Antonio Pérez-Ortiz; Felipe Sánchez-Martínez
Opublikowane w: Proceedings of the 28th International Conference on Computational Linguistics, 2020, Strona(/y) 3938–3950
Wydawca: International Committee on Computational Linguistics
DOI: 10.18653/v1/2020.coling-main.349

Sparse Communication via Mixed Distributions

Autorzy: Farinhas, António; Aziz, Wilker; Niculae, Vlad; Martins, André F. T.
Opublikowane w: Numer 1, 2022
Wydawca: ICLR
DOI: 10.48550/arxiv.2108.02658

Efficient marginalization of discrete and structured latent variables via sparsity

Autorzy: Correia, Gonçalo M.; Niculae, Vlad; Aziz, Wilker; Martins, André F. T.
Opublikowane w: Advances in Neural Information Processing Systems, 2020, Strona(/y) 11789-11802
Wydawca: Curran Associates, Inc.

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

Autorzy: Bawden, Rachel; Zhang, Biao; Tättar, Andre; Post, Matt
Opublikowane w: Proceedings of the Fifth Conference on Machine Translation, 2020, Strona(/y) 887–894
Wydawca: Association for Computational Linguistics

Cross-lingual Intermediate Fine-tuning improves Dialogue State Tracking

Autorzy: Moghe; Steedman; Birch
Opublikowane w: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021, Strona(/y) 1137–1150
Wydawca: Association for Computational Linguistics
DOI: 10.5281/zenodo.6672775

Widening the Representation Bottleneck in Neural Machine Translation with Lexical Shortcuts

Autorzy: Denis Emelin, Ivan Titov, Rico Sennrich
Opublikowane w: Proceedings of the Fourth Conference on Machine Translation (Volume 1: Research Papers), 2019, Strona(/y) 102-115
Wydawca: Association for Computational Linguistics
DOI: 10.18653/v1/w19-5211

Document Sub-structure in Neural Machine Translation

Autorzy: Dobreva, Radina; Zhou, Jie; Bawden, Rachel
Opublikowane w: Proceeding of the 12th Language Resources and Evaluation Conference, 2020, Strona(/y) 3657--3667, ISBN 979-10-95546-34-4
Wydawca: European Language Resources Association
DOI: 10.5281/zenodo.3923463

MultiWord Expression Aware Neural Machine Translation

Autorzy: Zaninello, Andrea; Birch, Alexandra
Opublikowane w: Proceedings of The 12th Language Resources and Evaluation Conference, 2020, Strona(/y) 3816-3825, ISBN 979-10-95546-34-4
Wydawca: European Language Resources Association
DOI: 10.5281/zenodo.3923509

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

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

Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation

Autorzy: Biao Zhang, Philip Williams, Ivan Titov, Rico Sennrich
Opublikowane w: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020, Strona(/y) 1628-1639
Wydawca: Association for Computational Linguistics
DOI: 10.18653/v1/2020.acl-main.148

Interpretable Neural Predictions with Differentiable Binary Variables

Autorzy: Joost Bastings, Wilker Aziz, Ivan Titov
Opublikowane w: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019, Strona(/y) 2963-2977
Wydawca: Association for Computational Linguistics
DOI: 10.18653/v1/p19-1284

Auto-Encoding Variational Neural Machine Translation

Autorzy: Bryan Eikema, Wilker Aziz
Opublikowane w: Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019), Numer Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019), 2019, Strona(/y) 124-141
Wydawca: Association for Computational Linguistics
DOI: 10.18653/v1/w19-4315

Effective Estimation of Deep Generative Language Models

Autorzy: Tom Pelsmaeker, Wilker Aziz
Opublikowane w: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020, Strona(/y) 7220-7236
Wydawca: Association for Computational Linguistics
DOI: 10.18653/v1/2020.acl-main.646

Block Neural Autoregressive Flow

Autorzy: De Cao, Nicola; Titov, Ivan; Aziz, Wilker
Opublikowane w: Proceedings of the Thirty-Fifth Conference on Uncertainty in Artificial Intelligence, UAI 2019, 2019, Strona(/y) 15
Wydawca: Association for Uncertainty in Artificial Intelligence

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

Autorzy: Duygu Ataman, Orhan Firat, Mattia A. Di Gangi, Marcello Federico, Alexandra Birch
Opublikowane w: Proceedings of the 3rd Workshop on Neural Generation and Translation, 2019, Strona(/y) 187-193
Wydawca: Association for Computational Linguistics
DOI: 10.18653/v1/D19-5619

A Latent Morphology Model for Open-Vocabulary Neural Machine Translation

Autorzy: Ataman, Duygu; Aziz, Wilker; Birch, Alexandra
Opublikowane w: Proceedings of the International Conference on Learning Representations 2020, 2020
Wydawca: International Conference on Learning Representations

Findings of the 2019 Conference on Machine Translation (WMT19)

Autorzy: 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
Opublikowane w: Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), 2019, Strona(/y) 1-61
Wydawca: 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

Autorzy: Scarton, Scarton; Forcada, Mikel L.; Esplà-Gomis, Miquel; Specia, Lucia
Opublikowane w: Proceedings of the 16th International Workshop on Spoken Language Translation 2019, Numer 10, 2019
Wydawca: 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

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

Towards Making the Most of Context in Neural Machine Translation

Autorzy: Zaixiang Zheng, Xiang Yue, Shujian Huang, Jiajun Chen, Alexandra Birch
Opublikowane w: Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, 2020, Strona(/y) 3983-3989, ISBN 978-0-9992411-6-5
Wydawca: 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

Autorzy: Oncevay, Arturo; Haddow, Barry; Birch, Alexandra
Opublikowane w: Proceedings of TyP-NLP: The First Workshop on Typology for Polyglot NLP, 2019
Wydawca: Association for Computational Linguistics
DOI: 10.5281/zenodo.3923625

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

Autorzy: Coleman, Susie; Secker, Andrew; Bawden, Rachel; Haddow, Barry; Birch, Alexandra
Opublikowane w: Proceedings of the 1st International Workshop on Language Technology Platforms, 2020, Strona(/y) 16–21
Wydawca: 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

Autorzy: Víctor M. Sánchez-Cartagena, Juan Antonio Pérez-Ortiz, Felipe Sánchez-Martínez
Opublikowane w: Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), 2019, Strona(/y) 356-363
Wydawca: Association for Computational Linguistics
DOI: 10.18653/v1/w19-5339

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

Autorzy: Sánchez-Cartagena, Víctor M.; Forcada, Mikel L.; Sánchez-Martínez, Felipe
Opublikowane w: Proceedings of the 22nd Annual Conference of the European Association for Machine Translation, 2020, Strona(/y) 61–70
Wydawca: European Association for Machine Translation
DOI: 10.5281/zenodo.3923596

Global Under-Resourced Media Translation (GoURMET)

Autorzy: 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
Opublikowane w: Proceedings of Machine Translation Summit XVII Volume 2: Translator, Project and User Tracks, 2019, Strona(/y) 122–122
Wydawca: European Association for Machine Translation

Highly Parallel Autoregressive Entity Linking with Discriminative Correction

Autorzy: De Cao, Nicola; Aziz, Wilker; Titov, Ivan
Opublikowane w: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021, Strona(/y) 7662–7669
Wydawca: Association for Computational Linguistics
DOI: 10.18653/v1/2021.emnlp-main.604

Distributionally Robust Recurrent Decoders with Random Network Distillation

Autorzy: Miceli Barone; Birch; Sennrich
Opublikowane w: Proceedings of the 7th Workshop on Representation Learning for NLP, 2022, Strona(/y) 1–8
Wydawca: Association for Computational Linguistics
DOI: 10.5281/zenodo.6672752

On Sparsifying Encoder Outputs in Sequence-to-Sequence Models

Autorzy: Biao Zhang; Ivan Titov; Rico Sennrich
Opublikowane w: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, 2021, Strona(/y) 2888–2900
Wydawca: Association for Computational Linguistics
DOI: 10.5167/uzh-208878

Exploring Unsupervised Pretraining Objectives for Machine Translation

Autorzy: Christos Baziotis; Ivan Titov; Alexandra Birch; Barry Haddow
Opublikowane w: Numer 1, 2021
Wydawca: ACL
DOI: 10.48550/arxiv.2106.05634

Towards Machine Translation for the Kurdish Language

Autorzy: Ahmadi, Sina; Masoud, Mariam
Opublikowane w: Proceedings of the 3rd Workshop on Technologies for MT of Low Resource Languages, 2020, Strona(/y) 87–98
Wydawca: Association for Computational Linguistics

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

Autorzy: Helcl; Haddow; Birch
Opublikowane w: EMNLP, Numer 5, 2022
Wydawca: ACL
DOI: 10.5281/zenodo.6672769

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

Autorzy: Espla-Gomis; Sanchez-Cartagena; Zaragoza-Bernabeu; Sanchez-Martinez
Opublikowane w: Proceedings of the Fifth Conference on Machine Translation, 2020, Strona(/y) 952–958
Wydawca: 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

Autorzy: 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
Opublikowane w: Proceedings of Machine Translation Summit XVIII: Research Track, 2021, Strona(/y) 92–102
Wydawca: Association for Machine Translation in the Americas
DOI: 10.5281/zenodo.6580252

Cross-lingual Intermediate Fine-tuning improves Dialogue State Tracking

Autorzy: Moghe; Steedman; Birch
Opublikowane w: Numer 3, 2021
Wydawca: ACL
DOI: 10.5281/zenodo.6672774

Language Model Prior for Low-Resource Neural Machine Translation

Autorzy: Christos Baziotis; Barry Haddow; Alexandra Birch
Opublikowane w: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020, Strona(/y) 7622–7634
Wydawca: Association for Computational Linguistics
DOI: 10.18653/v1/2020.emnlp-main.615

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

Autorzy: Bawden, Rachel; Bogoychev, Nikolay; Germann, Ulrich; Grundkiewicz, Roman; Kirefu, Faheem; Miceli Barone, Antonio Valerio; Birch, Alexandra
Opublikowane w: Numer 1, 2019
Wydawca: ACL
DOI: 10.48550/arxiv.1907.05854

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

Autorzy: Bawden, Rachel; Bogoychev, Nikolay; Germann, Ulrich; Grundkiewicz, Roman; Kirefu, Faheem; Miceli Barone, Antonio Valerio; Birch, Alexandra
Opublikowane w: Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), 2019, Strona(/y) 103–115
Wydawca: Association for Computational Linguistics

Towards Machine Translation for the Kurdish Language

Autorzy: Ahmadi, Sina; Masoud, Mariam
Opublikowane w: Numer 3, 2020
Wydawca: ACL
DOI: 10.48550/arxiv.2010.06041

Distributionally Robust Recurrent Decoders with Random Network Distillation

Autorzy: Miceli-Barone, Antonio Valerio; Birch, Alexandra; Sennrich, Rico
Opublikowane w: Numer 1, 2022
Wydawca: ACL
DOI: 10.5281/zenodo.6672751

Sampling-Based Minimum Bayes Risk Decoding for Neural Machine Translation

Autorzy: Eikema, Bryan; Aziz, Wilker
Opublikowane w: 2021
Wydawca: arxiv.org

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

Autorzy: Haddow, Barry; Kirefu, Faheem
Opublikowane w: 2020
Wydawca: arxiv.org

Sparse Communication via Mixed Distributions

Autorzy: Farinhas, António; Aziz, Wilker; Niculae, Vlad; Martins, André F. T.
Opublikowane w: 2021
Wydawca: arxiv.org

Block Neural Autoregressive Flow

Autorzy: De Cao, Nicola; Titov, Ivan; Aziz, Wilker
Opublikowane w: 2019
Wydawca: arxiv.org

Revisiting Neural Language Modelling with Syllables

Autorzy: Oncevay, Arturo; Rojas, Kervy Rivas
Opublikowane w: 2020
Wydawca: arxiv.org

Latent Transformations for Discrete-Data Normalising Flows

Autorzy: Hesselink, Rob; Aziz, Wilker
Opublikowane w: 2020
Wydawca: arxiv.org

Survey of Low-Resource Machine Translation

Autorzy: Haddow; Bawden; Miceli Barone; Helcl; Birch
Opublikowane w: Computational Linguistics, 2022, ISSN 0891-2017
Wydawca: MIT Press
DOI: 10.5281/zenodo.6672725

Wyszukiwanie danych OpenAIRE...

Rezultaty

Publikacje

Udostępnij tę stronę

Pobierz