European Live Translator

Deliverables

Public Project Web Site and Updates. The first version will be available after the third month of the project duration and it will be continuously updated and checked, esp. after 12., 24., and 36 months.

Initial Training Data, Separating Confidential and Public Version

Year 1 Test Sets

Year 2 Test Sets

Initial Report on Summarization

Report on NLP Technologies Workshop at EUROSAI Congress

Report 1 on Spoken Language Translation

Report on Dissemination Activites: Intermediate, Final

The Intermediate Report on Dissemination Activites will be published by 18th month of the project, the Final Report on Dissemination Activites will be prepared at the end of the project (36th month).

Initial Report on Multi-Lingual MT

Report 1 on Initial ASR Systems

Publishing Platform

Searching for OpenAIRE data...

Publications

On Sparsifying Encoder Outputs in Sequence-to-Sequence Models

Author(s): Zhang, Biao; Titov, Ivan; Sennrich, Rico
Published in: arXiv e-print, 2020

Human or Machine: Automating Human Likeliness Evaluation of NLG Texts

Author(s): Çano, Erion; Bojar, Ondřej
Published in: arXiv e-print, 2020

Dynamic Masking for Improved Stability in Spoken Language Translation

Author(s): Yao, Yuekun; Haddow, Barry
Published in: arXiv e-prints, Issue 1, 2020

Adaptive Feature Selection for End-to-End Speech Translation

Author(s): Biao Zhang; Ivan Titov; Barry Haddow; Rico Sennrich
Published in: arXiv e-print, 2020

CUNI Systems for the Unsupervised News Translation Task in WMT 2019

Author(s): Ivana Kvapilíková, Dominik Macháček, Ondřej Bojar
Published in: Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), 2019, Page(s) 241-248
DOI: 10.18653/v1/w19-5323

Towards Stream Translation: Adaptive Computation Time for Simultaneous Machine Translation

Author(s): Felix Schneider; Alex Waibel
Published in: Proceedings of the 17th International Conference on Spoken Language Translation, 2020

Neural Codes to Factor Language in Multilingual Speech Recognition

Author(s): Markus Müller; Sebastian Stüker; Alex Waibel
Published in: In proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2019

Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation

Author(s): Zhang, Biao; Williams, Philip; Titov, Ivan; Sennrich, Rico
Published in: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Issue 25, 2020
DOI: 10.5167/uzh-188226

Improving Deep Transformer with Depth-Scaled Initialization and Merged Attention

Author(s): Rico Sennrich
Published in: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing; all authors: Rico Sennrich; Biao Zhang; Ivan Titov, Issue 12, 2019
DOI: 10.5167/uzh-176330

Context-Aware Monolingual Repair for Neural Machine Translation

Author(s): Rico Sennrich
Published in: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP); all authors: Elena Voita; Rico Sennrich, Ivan Titov, Issue 13, 2019
DOI: 10.5167/uzh-176331

Improving sequence-to-sequence speech recognition training with on-the-fly data augmentation

Author(s): Thai-Son Nguyen; Sebastian Stüke;r Jan Niehues; Alex Waibel
Published in: In Proceedings of the 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020

Towards Automatic Minuting of Meetings

Author(s): Nedoluzhko, Anna; Bojar, Ondřej
Published in: Proceedings of the 19th Conference ITAT 2019: Slovenskočeský NLP workshop (SloNLP 2019), Issue 7, 2019

Modeling Confidence in Sequence-to-Sequence Models

Author(s): Niehues, Jan; Pham, Ngoc-Quan
Published in: In Proceedings of the 12th International Conference on Natural Language Generation - INLG, Issue 13, 2019

Keyphrase Generation: A Multi-Aspect Survey

Author(s): Erion Cano, Ondrej Bojar
Published in: 2019 25th Conference of Open Innovations Association (FRUCT), 2019, Page(s) 85-94
DOI: 10.23919/FRUCT48121.2019.8981519

SAO WMT19 Test Suite: Machine Translation of Audit Reports

Author(s): Tereza Vojtěchová, Michal Novák, Miloš Klouček, Ondřej Bojar
Published in: Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), 2019, Page(s) 481-493
DOI: 10.18653/v1/w19-5355

Efficiency Metrics for Data-Driven Models: A Text Summarization Case Study

Author(s): Erion Çano, Ondřej Bojar
Published in: Proceedings of the 12th International Conference on Natural Language Generation, 2019, Page(s) 229-239
DOI: 10.18653/v1/w19-8630

Very Deep Self-Attention Networks for End-to-End Speech Recognition

Author(s): Pham, Ngoc-Quan; Nguyen, Thai-Son; Niehues, Jan; Müller, Markus; Stüker, Sebastian; Waibel, Alexander
Published in: In Proceedings of the 20th Annual Conference of the International Speech Communication Association, INTERSPEECH 2019, Issue 4, 2019

When a Good Translation is Wrong in Context: Context-Aware Machine Translation Improves on Deixis, Ellipsis, and Lexical Cohesion

Author(s): Rico Sennrich
Published in: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics; all authors: Elena Voita; Rico Sennrich, Ivan Titov, Issue 12, 2019
DOI: 10.5167/uzh-172620

Root Mean Square Layer Normalization

Author(s): Zhang, Biao; Sennrich, Rico
Published in: Advances in Neural Information Processing Systems 32, Issue 19, 2019
DOI: 10.5167/uzh-177483

Self-Attentional Models for Lattice Inputs

Author(s): Sperber, Matthias; Neubig, Graham; Pham, Ngoc-Quan; Waibel, Alex
Published in: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics,, Issue 3, 2019, Page(s) 1185–1197

A Test Suite and Manual Evaluation of Document-Level NMT at WMT19

Author(s): Rysová, Magdaléna; Poláková, Lucie; Rysová, Kateřina; Bojar, Ondřej; Musil, Tomáš
Published in: Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), Issue 5, 2019

Toward Cross-Domain Speech Recognition with End-to-End Models

Author(s): Thai-Son Nguyen; Sebastian Stüker; Alex Waibel
Published in: In Proceedings of the Life Long Learning for Spoken Language Systems Workshop colocated with ASRU 2019, 2019

KIT's Submission to the IWSLT 2019 Shared Task on Text Translation

Author(s): Felix Schneider; Alex Waibel
Published in: In Proceedings of the 16th International Workshop on Spoken Language Translation 2019 --- IWSLT, 2019

Improving Zero-shot Translation with Language-Independent Constraints

Author(s): Pham, Ngoc-Quan; Niehues, Jan; Ha, Thanh-Le; Waibel, Alex
Published in: In proceedings of the 4th Conference in Machine Translation (WMT), ACL 2019, Issue 4, 2019

ELITR Non-Native Speech Translation at IWSLT 2020

Author(s): Macháček, Dominik; Kratochvíl, Jonáš; Sagar, Sangeet; Žilinec, Matúš; Bojar, Ondřej; Nguyen, Thai-Son; Schneider, Felix; Williams, Philip; Yao, Yuekun
Published in: Proceedings of the 17th International Conference on Spoken Language Translation (IWSLT 2020), Issue 11, 2020

Removing European Language Barriers with Innovative Machine Translation Technology

Author(s): Dario Franceschini; Chiara Canton; Ivan Simonini; Armin Schweinfurth; Adeleid Glott; Sebatian Stüker; Thai-Son Nguyen; Felix Schneider; Thanh-Le Ha; Alex Waibel; Barry Haddow; Philip Williams; Rico Sennrich; Ondřej Bojar; Sangeet Sagar; Dominik Macháček; Otakar Smrž
Published in: Proceedings of the 1st International Workshop on Language Technology Platforms, 2020

High Performance Sequence-to-Sequence Model for Streaming Speech Recognition

Author(s): Thai-Son Nguyen; Ngoc-Quan Pham; Sebastian Stüker; Alex Waibel
Published in: To appear in Proceedings of the 21st INTERSPEECH, 2020

The IWSLT 2019 KIT Speech Translation System

Author(s): Ngoc-Quan Pham; Thai-Son Nguyen; Thanh-Le Ha; Juan Hussain; Felix Schneider; Jan Niehues; Sebastian Stüker; Alexander Waibel
Published in: In Proceedings of the 16th International Workshop on Spoken Language Translation 2019 --- IWSLT, 2019

Two Huge Title and Keyword Generation Corpora of Research Articles

Author(s): Çano, Erion; Bojar, Ondřej
Published in: Proceedings of The 12th Language Resources and Evaluation Conference, Issue 21, 2020

Keyphrase Generation: A Text Summarization Struggle

Author(s): Erion Çano, Ondřej Bojar
Published in: Proceedings of the 2019 Conference of the North, 2019, Page(s) 666-672
DOI: 10.18653/v1/N19-1070

Attention-Passing Models for Robust and Data-Efficient End-to-End Speech Translation

Author(s): Sperber, Matthias; Neubig, Graham; Niehues, Jan; Waibel, Alex
Published in: Transactions of the Association for Computational Linguistics, Issue 7, 2019, ISSN 2307-387X

Promoting the Knowledge of Source Syntax in Transformer NMT Is Not Needed

Author(s): Thuong Hai Pham, Dominik Macháček, Ondřej Bojar
Published in: Computación y Sistemas, Issue 23/3, 2019, ISSN 1405-5546
DOI: 10.13053/cys-23-3-3265

A Speech Test Set of Practice Business Presentations with Additional Relevant Texts

Author(s): Dominik Macháček, Jonáš Kratochvíl, Tereza Vojtěchová, Ondřej Bojar
Published in: Statistical Language and Speech Processing - 7th International Conference, SLSP 2019, Ljubljana, Slovenia, October 14–16, 2019, Proceedings, Issue 11816, 2019, Page(s) 151-161
DOI: 10.1007/978-3-030-31372-2_13

Deliverables

Publications

Share this page

Download