European Live Translator

Livrables

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.

Demonstrator of Automatic Minuting
Publishing Platform

Final Report on Summarization
Intermediate Report on Multi-Lingual MT

Intermediate Report on MultiLingual MT

Report 2 on ASR Systems
Final Report on Multi-Lingual MT

Final Report on MultiLingual MT

Initial Report on Summarization
Report on NLP Technologies Workshop at EUROSAI Congress
Report 1 on Spoken Language Translation
Report on Follow-up SAO Events

Report on Followup SAO Events

Final Report on Integration
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
Intermediate Report on Integration
Report 1 on Initial ASR Systems
Report 2 on Spoken Language Translation
Report on ELITR at EUROSAI Congress

Final Training Data, Separating Confidential and Public Version

Final Training Data Separating Confidential and Public Version

Initial Training Data, Separating Confidential and Public Version
Year 1 Test Sets
Year 3 Test Sets
Year 2 Test Sets

Publications

ELITR: European Live Translator

Auteurs: Haddow, Barry; Sagar, Sangeet; Simonini, Ivan; Franceschini, Dario; Stüker, Sebastian; Sennrich, Rico; Nguyen, Thai-Son; Macháček, Dominik; Canton, Chiara; Ansari, Ebrahim; Smrž, Otakar; Williams, Philip; Waibel, Alex; Kratochvíl, Jonáš; Schneider, Felix; Bojar, Ondřej
Publié dans: Numéro 1, 2020
Éditeur: European Association for Machine Translation

Adaptive Feature Selection for End-to-End Speech Translation

Auteurs: Biao Zhang; Ivan Titov; Barry Haddow; Rico Sennrich
Publié dans: Zhang , B , Titov , I , Haddow , B & Sennrich , R 2020 , Adaptive Feature Selection for End-to-End Speech Translation . in Findings of the Association for Computational Linguistics: EMNLP 2020 . pp. 2533-2544 , The 2020 Conference on Empirical Methods in Natural Language Processing , Virtual conference , 16/11/20 . https://doi.org/10.18653/v1/2020.findings-emnlp.230, Numéro 11, 2020
Éditeur: Association for Computational Linguistics
DOI: 10.5167/uzh-191666

CUNI Systems for the Unsupervised News Translation Task in WMT 2019

Auteurs: Ivana Kvapilíková, Dominik Macháček, Ondřej Bojar
Publié dans: Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), 2019, Page(s) 241-248
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/w19-5323

Towards Stream Translation: Adaptive Computation Time for Simultaneous Machine Translation

Auteurs: Felix Schneider; Alex Waibel
Publié dans: Proceedings of the 17th International Conference on Spoken Language Translation, 2020
Éditeur: ACL

Neural Codes to Factor Language in Multilingual Speech Recognition

Auteurs: Markus Müller; Sebastian Stüker; Alex Waibel
Publié dans: In proceedings of the International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2019
Éditeur: IEEE

Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation

Auteurs: Zhang, Biao; Williams, Philip; Titov, Ivan; Sennrich, Rico
Publié dans: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Numéro 25, 2020
Éditeur: ACL
DOI: 10.5167/uzh-188226

FINDINGS OF THE IWSLT 2020 EVALUATION CAMPAIGN

Auteurs: Ebrahim Ansari; Amittai Axelrod; Nguyen Bach; Ondrej Bojar; Roldano Cattoni; Fahim Dalvi; Nadir Durrani; Marcello Federico; Christian Federmann; Jiatao Gu; Fei Huang; Kevin Knight; Xutai Ma; Ajay Nagesh; Matteo Negri; Jan Niehues; Juan Pino; Elizabeth Salesky; Xing Shi; Sebastian Stüker; Marco Turchi; Alex Waibel; Changhan Wang
Publié dans: 17TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE TRANSLATION (IWSLT 2020), Numéro 4, 2020
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2020.iwslt-1.1

Removing European Language Barriers with Innovative Machine Translation Technology

Auteurs: Bojar, Ondřej; Macháček, Dominik; Ha, Thanh-Le; Simonini, Ivan; Franceschini, Dario; Williams, Phil; Stüker, Sebastian; Sagar, Sangeet; Nguyen, Thai-Son; Schneider, Felix; Waibel, Alex; Canton, Chiara; Smrž, Otakar; Glott, Adelheid; Haddow, Barry; Sennrich, Rico; Schweinfurth, Armin
Publié dans: Numéro 1, 2020
Éditeur: European Language Resources Association

Efficient Weight factorization for Multilingual Speech Recognition

Auteurs: Ngoc-Quan Pham; Tuan-Nam Nguyen; Sebastian Stüker; Alex Waibel
Publié dans: Numéro 1, 2021
Éditeur: ISCA
DOI: 10.21437/interspeech.2021-216

ELITR Multilingual Live Subtitling: Demo and Strategy

Auteurs: Ondřej Bojar; Dominik Macháček; Sangeet Sagar; Otakar Smrž; Jonáš Kratochvíl; Peter Polák; Ebrahim Ansari; Mohammad Mahmoudi; Rishu Kumar; Dario Franceschini; Chiara Canton; Ivan Simonini; Thai-Son Nguyen; Felix Schneider; Sebastian Stüker; Alex Waibel; Barry Haddow; Rico Sennrich; Philip Williams
Publié dans: EACL (System Demonstrations), Numéro 5, 2021
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2021.eacl-demos.32

Improving Deep Transformer with Depth-Scaled Initialization and Merged Attention

Auteurs: Rico Sennrich
Publié dans: 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, Numéro 12, 2019
Éditeur: ACL
DOI: 10.5167/uzh-176330

Context-Aware Monolingual Repair for Neural Machine Translation

Auteurs: Rico Sennrich
Publié dans: 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, Numéro 13, 2019
Éditeur: ACL
DOI: 10.5167/uzh-176331

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

Auteurs: Thai-Son Nguyen; Sebastian Stüke;r Jan Niehues; Alex Waibel
Publié dans: In Proceedings of the 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020
Éditeur: IEEE

Operating a Complex SLT System with Speakers and Human Interpreters

Auteurs: Srdečný, Vojtěch; Williams, Phil; Schneider, Felix; Canton, Chiara; Kumar, Rishu; Smrž, Otakar; Haddow, Barry; Bojar, Ondřej
Publié dans: Numéro 16, 2021
Éditeur: Association for Machine Translation in the Americas

Towards Automatic Minuting of Meetings

Auteurs: Nedoluzhko, Anna; Bojar, Ondřej
Publié dans: Proceedings of the 19th Conference ITAT 2019: Slovenskočeský NLP workshop (SloNLP 2019), Numéro 7, 2019
Éditeur: CreateSpace Independent Publishing Platform

Modeling Confidence in Sequence-to-Sequence Models

Auteurs: Niehues, Jan; Pham, Ngoc-Quan
Publié dans: In Proceedings of the 12th International Conference on Natural Language Generation - INLG, Numéro 13, 2019
Éditeur: ACL

Keyphrase Generation: A Multi-Aspect Survey

Auteurs: Erion Cano, Ondrej Bojar
Publié dans: 2019 25th Conference of Open Innovations Association (FRUCT), 2019, Page(s) 85-94, ISBN 978-952-69244-0-3
Éditeur: IEEE
DOI: 10.23919/FRUCT48121.2019.8981519

SAO WMT19 Test Suite: Machine Translation of Audit Reports

Auteurs: Tereza Vojtěchová, Michal Novák, Miloš Klouček, Ondřej Bojar
Publié dans: Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), 2019, Page(s) 481-493
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/w19-5355

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

Auteurs: Erion Çano, Ondřej Bojar
Publié dans: Proceedings of the 12th International Conference on Natural Language Generation, 2019, Page(s) 229-239
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/w19-8630

Lost in Interpreting: Speech Translation from Source or Interpreter?

Auteurs: Dominik Machácek; Matús Zilinec; Ondrej Bojar
Publié dans: Proc. Interspeech 2021, Numéro 1, 2021
Éditeur: ISCA
DOI: 10.21437/interspeech.2021-2232

On Sparsifying Encoder Outputs in Sequence-to-Sequence Models

Auteurs: Biao Zhang; Ivan Titov; Rico Sennrich
Publié dans: Zhang , B , Titov , I & Sennrich , R 2021 , On Sparsifying Encoder Outputs in Sequence-to-Sequence Models . in Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021 . Online , pp. 2888-2900 , The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing , Bangkok , Tha, Numéro 11, 2021
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2021.findings-acl.255

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

Auteurs: Pham, Ngoc-Quan; Nguyen, Thai-Son; Niehues, Jan; Müller, Markus; Stüker, Sebastian; Waibel, Alexander
Publié dans: In Proceedings of the 20th Annual Conference of the International Speech Communication Association, INTERSPEECH 2019, Numéro 4, 2019
Éditeur: International Speech Communication Association

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

Auteurs: Rico Sennrich
Publié dans: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics; all authors: Elena Voita; Rico Sennrich, Ivan Titov, Numéro 12, 2019
Éditeur: ACL
DOI: 10.5167/uzh-172620

Root Mean Square Layer Normalization

Auteurs: Zhang, Biao; Sennrich, Rico
Publié dans: Advances in Neural Information Processing Systems 32, Numéro 19, 2019
Éditeur: Conference on Neural Information Processing Systems
DOI: 10.5167/uzh-177483

FINDINGS OF THE IWSLT 2021 EVALUATION CAMPAIGN

Auteurs: Salesky, Elizabeth; Elbayad, Maha; Niehues, Jan; Ma, Xutai; Negri, Matteo; Stüker, Sebastian; Waibel, Alex; Federico, Marcello; Cattoni, Roldano; Bremerman, Jacob; Sudoh, Katsuhito; Turchi, Marco; Wang, Changhan; Nakamura, Satoshi; Anastasopoulos, Antonios; Pino, Juan; Bojar, Ondřej; Wiesner, Matthew
Publié dans: Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021), Numéro 4, 2021
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2021.iwslt-1.1

Self-Attentional Models for Lattice Inputs

Auteurs: Sperber, Matthias; Neubig, Graham; Pham, Ngoc-Quan; Waibel, Alex
Publié dans: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics,, Numéro 3, 2019, Page(s) 1185–1197
Éditeur: ACL

ELITR Non-Native Speech Translation at IWSLT 2020

Auteurs: Dominik Macháček; Jonáš Kratochvíl; Sangeet Sagar; Matúš Žilinec; Ondřej Bojar; Thai-Son Nguyen; Felix Schneider; Philip Williams; Yuekun Yao
Publié dans: Crossref, Numéro 2, 2020
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2020.iwslt-1.25

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

Auteurs: Rysová, Magdaléna; Poláková, Lucie; Rysová, Kateřina; Bojar, Ondřej; Musil, Tomáš
Publié dans: Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1), Numéro 5, 2019
Éditeur: ACL

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

Auteurs: Thai-Son Nguyen; Sebastian Stüker; Alex Waibel
Publié dans: In Proceedings of the Life Long Learning for Spoken Language Systems Workshop colocated with ASRU 2019, 2019
Éditeur: ASRU

SLTEV: Comprehensive Evaluation of Spoken Language Translation

Auteurs: Ebrahim Ansari; Ondřej Bojar; Barry Haddow; Mohammad Mahmoudi
Publié dans: EACL (System Demonstrations), Numéro 6, 2021
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2021.eacl-demos.9

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

Auteurs: Felix Schneider; Alex Waibel
Publié dans: In Proceedings of the 16th International Workshop on Spoken Language Translation 2019 --- IWSLT, 2019
Éditeur: IWSLT

Improving Zero-shot Translation with Language-Independent Constraints

Auteurs: Pham, Ngoc-Quan; Niehues, Jan; Ha, Thanh-Le; Waibel, Alex
Publié dans: In proceedings of the 4th Conference in Machine Translation (WMT), ACL 2019, Numéro 4, 2019
Éditeur: ACL

ELITR Non-Native Speech Translation at IWSLT 2020

Auteurs: Macháček, Dominik; Kratochvíl, Jonáš; Sagar, Sangeet; Žilinec, Matúš; Bojar, Ondřej; Nguyen, Thai-Son; Schneider, Felix; Williams, Philip; Yao, Yuekun
Publié dans: Proceedings of the 17th International Conference on Spoken Language Translation (IWSLT 2020), Numéro 11, 2020
Éditeur: IWSLT

Paper Length Prediction from the Metadata

Auteurs: Erion Çano; Ondřej Bojar
Publié dans: NLPIR, Numéro 2, 2020, ISBN 9781450377607
Éditeur: Association for Computing Machinery
DOI: 10.1145/3443279.3443305

Removing European Language Barriers with Innovative Machine Translation Technology

Auteurs: 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
Publié dans: Proceedings of the 1st International Workshop on Language Technology Platforms, 2020, ISBN 979-10-95546-64-1
Éditeur: ELRA

Large Corpus of Czech Parliament Plenary Hearings

Auteurs: Polák, Peter; Kratochvíl, Jonáš; Bojar, Ondřej
Publié dans: Numéro 1, 2020
Éditeur: European Language Resources Association

Improving Zero-shot Translation with Language-Independent Constraints

Auteurs: Ngoc-Quan Pham; Jan Niehues; Thanh-Le Ha; Alex Waibel
Publié dans: Proceedings of the Fourth Conference on Machine Translation (Volume 1: Research Papers), Numéro 2, 2019
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/w19-5202

Findings of the 2020 Conference on Machine Translation (WMT20)

Auteurs: Zampieri, Marcos; Kocmi, Tom; Barrault, Loïc; Ljubešić, Nikola; Morishita, Makoto; Lo, Chi-kiu; Nakazawa, Toshiaki; Pal, Santanu; Joanis, Eric; Costa-Jussà, Marta; Monz, Christof; Grundkiewicz, Roman; Huck, Matthias; Biesialska, Magdalena; Graham, Yvette; Nagata, Masaaki; Haddow, Barry; Koehn, Philipp; Bojar, Ondřej; Post, Matt; Federmann, Christian
Publié dans: Numéro 10, 2020
Éditeur: Association for Computational Linguistics

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

Auteurs: Thai-Son Nguyen; Ngoc-Quan Pham; Sebastian Stüker; Alex Waibel
Publié dans: To appear in Proceedings of the 21st INTERSPEECH, 2020
Éditeur: International Speech Communication Association

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

Auteurs: Kateřina Rysová; Magdaléna Rysová; Tomáš Musil; Lucie Poláková; Ondřej Bojar
Publié dans: WMT (2), Numéro 8, 2019
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/w19-5352

The IWSLT 2019 KIT Speech Translation System

Auteurs: Ngoc-Quan Pham; Thai-Son Nguyen; Thanh-Le Ha; Juan Hussain; Felix Schneider; Jan Niehues; Sebastian Stüker; Alexander Waibel
Publié dans: In Proceedings of the 16th International Workshop on Spoken Language Translation 2019 --- IWSLT, 2019
Éditeur: IWSLT

Two Huge Title and Keyword Generation Corpora of Research Articles

Auteurs: Çano, Erion; Bojar, Ondřej
Publié dans: Proceedings of The 12th Language Resources and Evaluation Conference, Numéro 21, 2020
Éditeur: ELRA

Keyphrase Generation: A Text Summarization Struggle

Auteurs: Erion Çano, Ondřej Bojar
Publié dans: Proceedings of the 2019 Conference of the North, 2019, Page(s) 666-672
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/N19-1070

CUNI Neural ASR with Phoneme-Level Intermediate Step for~Non-Native~SLT at IWSLT 2020

Auteurs: Peter Polák; Sangeet Sagar; Dominik Macháček; Ondřej Bojar
Publié dans: Crossref, Numéro 1, 2020
Éditeur: Association for Computational Linguistics
DOI: 10.18653/v1/2020.iwslt-1.24

Presenting Simultaneous Translation in Limited Space

Auteurs: Macháček, Dominik; Bojar, Ondřej
Publié dans: Proceedings of the 20th Conference Information Technologies - Applications and Theory (ITAT 2020), Numéro 3, 2020
Éditeur: CEUR-WS.org

WMT20 Document-Level Markable Error Exploration

Auteurs: Vojtěchová, Tereza; Zouhar, Vilém; Bojar, Ondřej
Publié dans: Numéro 5, 2020
Éditeur: Association for Computational Linguistics

Report on the SIGDial 2021 Special Session on Summarization of Dialogues and Multi-Party Meetings (SummDial)

Auteurs: Tirthankar Ghosal; Muskaan Singh; Anja Nedoluzhko; Ondřej Bojar
Publié dans: Crossref, Numéro 2, 2022, ISSN 0163-5840
Éditeur: Association for Computing Machinery
DOI: 10.1145/3527546.3527561

On Sparsifying Encoder Outputs in Sequence-to-Sequence Models

Auteurs: Zhang, Biao; Titov, Ivan; Sennrich, Rico
Publié dans: arXiv e-print, 2020
Éditeur: arXiv e-print

Human or Machine: Automating Human Likeliness Evaluation of NLG Texts

Auteurs: Çano, Erion; Bojar, Ondřej
Publié dans: arXiv e-print, 2020
Éditeur: arXiv e-print

Dynamic Masking for Improved Stability in Spoken Language Translation

Auteurs: Yao, Yuekun; Haddow, Barry
Publié dans: arXiv e-prints, Numéro 1, 2020
Éditeur: arXiv e-prints

Adaptive Feature Selection for End-to-End Speech Translation

Auteurs: Biao Zhang; Ivan Titov; Barry Haddow; Rico Sennrich
Publié dans: arXiv e-print, 2020
Éditeur: arXiv e-print

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

Auteurs: Sperber, Matthias; Neubig, Graham; Niehues, Jan; Waibel, Alex
Publié dans: Transactions of the Association for Computational Linguistics, Numéro 7, 2019, ISSN 2307-387X
Éditeur: MIT Press

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

Auteurs: Thuong Hai Pham, Dominik Macháček, Ondřej Bojar
Publié dans: Computación y Sistemas, Numéro 23/3, 2019, ISSN 1405-5546
Éditeur: Centro de Investigacion en Computacion (CIC) del Instituto Politecnico Nacional (IPN)
DOI: 10.13053/cys-23-3-3265

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

Auteurs: Dominik Macháček, Jonáš Kratochvíl, Tereza Vojtěchová, Ondřej Bojar
Publié dans: Statistical Language and Speech Processing - 7th International Conference, SLSP 2019, Ljubljana, Slovenia, October 14–16, 2019, Proceedings, Numéro 11816, 2019, Page(s) 151-161, ISBN 978-3-030-31371-5
Éditeur: Springer International Publishing
DOI: 10.1007/978-3-030-31372-2_13

ParCzech 3.0: A Large Czech Speech Corpus with Rich Metadata

Auteurs: Matyáš Kopp; Vladislav Stankov; Jan Oldřich Krůza; Pavel Straňák; Ondřej Bojar
Publié dans: TSD, Numéro 18, 2021
Éditeur: Springer
DOI: 10.1007/978-3-030-83527-9_25

Recherche de données OpenAIRE...

Livrables

Publications

Partager cette page

Télécharger