Opendata, web and dolomites

FoTran SIGNED

Found in Translation – Natural Language Understanding with Cross-Lingual Grounding

Total Cost €

0

EC-Contrib. €

0

Partnership

0

Views

0

Project "FoTran" data sheet

The following table provides information about the project.

Coordinator
HELSINGIN YLIOPISTO 

Organization address
address: YLIOPISTONKATU 3
city: HELSINGIN YLIOPISTO
postcode: 14
website: www.helsinki.fi

contact info
title: n.a.
name: n.a.
surname: n.a.
function: n.a.
email: n.a.
telephone: n.a.
fax: n.a.

 Coordinator Country Finland [FI]
 Total cost 1˙817˙622 €
 EC max contribution 1˙817˙622 € (100%)
 Programme 1. H2020-EU.1.1. (EXCELLENT SCIENCE - European Research Council (ERC))
 Code Call ERC-2017-COG
 Funding Scheme ERC-COG
 Starting year 2018
 Duration (year-month-day) from 2018-09-01   to  2023-08-31

 Partnership

Take a look of project's partnership.

# participants  country  role  EC contrib. [€] 
1    HELSINGIN YLIOPISTO FI (HELSINGIN YLIOPISTO) coordinator 1˙817˙622.00

Map

 Project objective

'Natural language understanding is the 'holy grail' of computational linguistics and a long-term goal in research on artificial intelligence. Understanding human communication is difficult due to the various ambiguities in natural languages and the wide range of contextual dependencies required to resolve them. Discovering the semantics behind language input is necessary for proper interpretation in interactive tools, which requires an abstraction from language-specific forms to language-independent meaning representations. With this project, I propose a line of research that will focus on the development of novel data-driven models that can learn such meaning representations from indirect supervision provided by human translations covering a substantial proportion of the linguistic diversity in the world. A guiding principle is cross-lingual grounding, the effect of resolving ambiguities through translation. The beauty of that idea is the use of naturally occurring data instead of artificially created resources and costly manual annotations. The framework is based on deep learning and neural machine translation and my hypothesis is that training on increasing amounts of linguistically diverse data improves the abstractions found by the model. Eventually, this will lead to universal sentence-level meaning representations and we will test our ideas with multilingual machine translation and tasks that require semantic reasoning and inference.'

 Publications

year authors and title journal last update
List of publications.
2019 Alessandro Raganato, Raúl Vázquez, Mathias Creutz, Jörg Tiedemann
An Evaluation of Language-Agnostic Inner-Attention-Based Representations in Machine Translation
published pages: 27-32, ISSN: , DOI: 10.18653/v1/w19-4304
Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019) 2020-04-24
2019 Yves Scherrer, Achim Rabus
Neural morphosyntactic tagging for Rusyn
published pages: 633-650, ISSN: 1351-3249, DOI: 10.1017/s1351324919000287
Natural Language Engineering 25/5 2020-04-24
2019 Alessandro Raganato, Yves Scherrer and Jörg Tiedemann
The MuCoW test suite at WMT 2019: Automatically harvested multilingual contrastive word sense disambiguation test sets for machine translation.
published pages: 470-480, ISSN: , DOI:
In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL): Student Research Workshop. 2019. 2020-04-24
2019 Yves Scherrer, Jörg Tiedemann, Sharid Loáiciga
Analysing concatenation approaches to document-level NMT in two different domains
published pages: 51-61, ISSN: , DOI: 10.18653/v1/d19-6506
Proceedings of the Fourth Workshop on Discourse in Machine Translation (DiscoMT 2019) 2020-04-24
2019 Jörg Tiedemann, Yves Scherrer
Measuring Semantic Abstraction of Multilingual
published pages: 35-42, ISSN: , DOI: 10.18653/v1/w19-2005
Proceedings of the 3rd Workshop on Evaluating Vector Space Representations for 2020-04-24
2019 Stratos Xenouleas, Prodromos Malakasiotis, Marianna Apidianaki, Ion Androutsopoulos
SUM-QE: a BERT-based Summary Quality Estimation Model
published pages: 6004-6010, ISSN: , DOI: 10.18653/v1/d19-1618
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) 2020-04-24
2019 Aarne Talman, Umut Sulubacak, Raúl Vázquez, Yves Scherrer, Sami Virpioja, Alessandro Raganato, Arvi Hurskainen, Jörg Tiedemann
The University of Helsinki Submissions to the WMT19 News Translation Task
published pages: 412-423, ISSN: , DOI: 10.18653/v1/w19-5347
Proceedings of the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1) 2020-04-24
2019 Raúl Vázquez, Alessandro Raganato, Jörg Tiedemann, Mathias Creutz
Multilingual NMT with a Language-Independent Attention Bridge
published pages: 33-39, ISSN: , DOI: 10.18653/v1/w19-4305
Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019) 2020-04-24
2019 Yves Scherrer, Raúl Vázquez, Sami Virpioja
The University of Helsinki Submissions to the WMT19 Similar Language Translation Task
published pages: 236-244, ISSN: , DOI: 10.18653/v1/w19-5432
Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2) 2020-04-24
2018 Franck Burlot, Yves Scherrer, Vinit Ravishankar, Ondřej Bojar, Stig-Arne Grönroos, Maarit Koponen, Tommi Nieminen, François Yvon
The WMT’18 Morpheval test suites for English-Czech, English-German, English-Finnish and Turkish-English
published pages: 546-560, ISSN: , DOI: 10.18653/v1/w18-6433
Proceedings of the Third Conference on Machine Translation: Shared Task Papers 2020-04-24
2018 Alessandro Raganato, Jörg Tiedemann
An Analysis of Encoder Representations in Transformer-Based Machine Translation
published pages: 287-297, ISSN: , DOI: 10.18653/v1/w18-5431
Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP 2020-04-24
2019 Raúl Vázquez, Umut Sulubacak, Jörg Tiedemann
The University of Helsinki Submission to the WMT19 Parallel Corpus Filtering Task
published pages: 294-300, ISSN: , DOI: 10.18653/v1/w19-5441
Proceedings of the Fourth Conference on Machine Translation (Volume 3: Shared Task Papers, Day 2) 2020-04-24
2019 Marcos Zampieri, Shervin Malmasi, Yves Scherrer, Tanja Samardžić, Francis Tyers, Miikka Silfverberg, Natalia Klyueva, Tung-Le Pan, Chu-Ren Huang, Radu Tudor Ionescu, Andrei M. Butnaru, Tommi Jauhiainen
A Report on the Third
published pages: 1-16, ISSN: , DOI: 10.18653/v1/w19-1401
Proceedings of the Sixth Workshop on 2020-04-24
2019 Talha Çolakoğlu, Umut Sulubacak and Ahmet Cüneyd Tantuğ
Normalizing Non-canonical Turkish Texts Using Machine Translation Approaches. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL): Student Research Workshop. 2019.
published pages: 267-272, ISSN: , DOI:
In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL): Student Research Workshop. 2019. 2020-04-24
2019 Johannes Bjerva, Robert Östling, Maria Han Veiga, Jörg Tiedemann, Isabelle Augenstein
What Do Language Representations Really Represent?
published pages: 381-389, ISSN: 0891-2017, DOI: 10.1162/coli_a_00351
Computational Linguistics 45/2 2020-04-24
2018 Alessandro Raganato, Yves Scherrer, Tommi Nieminen, Arvi Hurskainen, Jörg Tiedemann
The University of Helsinki submissions to the WMT18 news task
published pages: 488-495, ISSN: , DOI: 10.18653/v1/w18-6425
Proceedings of the Third Conference on Machine Translation: Shared Task Papers 2020-04-24

Are you the coordinator (or a participant) of this project? Plaese send me more information about the "FOTRAN" project.

For instance: the website url (it has not provided by EU-opendata yet), the logo, a more detailed description of the project (in plain text as a rtf file or a word file), some pictures (as picture files, not embedded into any word file), twitter account, linkedin page, etc.

Send me an  email (fabio@fabiodisconzi.com) and I put them in your project's page as son as possible.

Thanks. And then put a link of this page into your project's website.

The information about "FOTRAN" are provided by the European Opendata Portal: CORDIS opendata.

More projects from the same programme (H2020-EU.1.1.)

iNANOVAC4CANCER (2019)

BIOHYBRID AND BIODEGRADABLE NANOVACCINES FOR CANCER IMMUNOTHERAPY

Read More  

KEYNESGROWTH (2020)

Economic Fluctuations, Productivity Growth and Stabilization Policies: A Keynesian Growth Perspective

Read More  

DISINTEGRATION (2019)

The Mass Politics of Disintegration

Read More