Opendata, web and dolomites

DeepSPIN SIGNED

Deep Learning for Structured Prediction in Natural Language Processing

Total Cost €

0

EC-Contrib. €

0

Partnership

0

Views

0

 DeepSPIN project word cloud

Explore the words cloud of the DeepSPIN project. It provides you a very rough idea of what is the project "DeepSPIN" about.

crowd    simplistic    supervision    structurally    inducing    breakthroughs    missing    learning    sourcing    words    structure    world    service    combinatorial    leads    weak    revolutionizing    seamless    messenger    language    recognition    bots    interdependent    serious    digital    translation    maximize    answering    complexity    broadly    bridge    scalable    probabilistic    quality    mistranslated    dropped    attacks    prone    communication    machine    optimal    networks    mechanisms    question    parsing    operate    interfaces    start    automatically    technologies    solving    human    entities    perspective    optimization    inside    ignore    natural    apps    innovations    prediction    structured    labeled    reasoning    ways    assistants    letting    cross    exploited    deep    modeling    fundamental    endow    speech    reduce    relying    output    search    dependency    techniques    mistakes    disciplinary    latent    network    named    guide    estimation    decoders    first    complement    planning    customer    technological    requiring    synergies    machines    predicting    sparse    disruptive    neural    testbeds    inference    error    greedy    serve    humans    interpretable    data    nlp    multilingual    variables    involve    incorporating    structural    company    mechanism    expressive    industry   

Project "DeepSPIN" data sheet

The following table provides information about the project.

Coordinator
INSTITUTO DE TELECOMUNICACOES 

Organization address
address: CAMPUS UNIVERSITARIO DE SANTIAGO UNIVERSIDADE DE AVEIRO
city: GLORIA E VERA CRUZ
postcode: 3810 193
website: www.it.pt

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 Portugal [PT]
 Project website https://deep-spin.github.io
 Total cost 1˙436˙000 €
 EC max contribution 1˙436˙000 € (100%)
 Programme 1. H2020-EU.1.1. (EXCELLENT SCIENCE - European Research Council (ERC))
 Code Call ERC-2017-STG
 Funding Scheme ERC-STG
 Starting year 2018
 Duration (year-month-day) from 2018-02-01   to  2023-01-31

 Partnership

Take a look of project's partnership.

# participants  country  role  EC contrib. [€] 
1    INSTITUTO DE TELECOMUNICACOES PT (GLORIA E VERA CRUZ) coordinator 1˙336˙000.00
2    UNBABEL, LDA PT (SAMORA CORREIA) participant 100˙000.00

Map

 Project objective

Deep learning is revolutionizing the field of Natural Language Processing (NLP), with breakthroughs in machine translation, speech recognition, and question answering. New language interfaces (digital assistants, messenger apps, customer service bots) are emerging as the next technologies for seamless, multilingual communication among humans and machines.

From a machine learning perspective, many problems in NLP can be characterized as structured prediction: they involve predicting structurally rich and interdependent output variables. In spite of this, current neural NLP systems ignore the structural complexity of human language, relying on simplistic and error-prone greedy search procedures. This leads to serious mistakes in machine translation, such as words being dropped or named entities mistranslated. More broadly, neural networks are missing the key structural mechanisms for solving complex real-world tasks requiring deep reasoning.

This project attacks these fundamental problems by bringing together deep learning and structured prediction, with a highly disruptive and cross-disciplinary approach. First, I will endow neural networks with a 'planning mechanism' to guide structural search, letting decoders learn the optimal order by which they should operate. This makes a bridge with reinforcement learning and combinatorial optimization. Second, I will develop new ways of automatically inducing latent structure inside the network, making it more expressive, scalable and interpretable. Synergies with probabilistic inference and sparse modeling techniques will be exploited. To complement these two innovations, I will investigate new ways of incorporating weak supervision to reduce the need for labeled data.

Three highly challenging applications will serve as testbeds: machine translation, quality estimation, and dependency parsing. To maximize technological impact, a collaboration is planned with a start-up company in the crowd-sourcing translation industry.

 Publications

year authors and title journal last update
List of publications.
2019 António Góis and André F. T. Martins
Translator2Vec: Understanding and Representing Human Post-Editors
published pages: , ISSN: , DOI:
Proceedings of Machine Translation Summit XVII Volume 1: Research Track (MT Summit 2019) 2019-08-29
2019 Gonçalo M. Correia, André F. T. Martins
A Simple and Effective Approach to Automatic Post-Editing with Transfer Learning
published pages: , ISSN: , DOI:
Annual Meeting of the Association for Computational Linguistics (ACL\'19) 2019-08-29
2019 António V. Lopes, M. Amin Farajian, Gonçalo M. Correia, Jonay Trénous, André F. T. Martins
Unbabel\'s Submission to the WMT2019 APE Shared Task: BERT-Based Encoder-Decoder for Automatic Post-Editing
published pages: , ISSN: , DOI:
Conference on Machine Translation (WMT 2019) 2019-08-29
2019 Maruf, Sameen; Martins, André F. T.; Haffari, Gholamreza
Selective Attention for Context-aware Neural Machine Translation
published pages: , ISSN: , DOI:
Proceedings of the North-American Chapter of the Association for Computational Linguistics 1 2019-08-29
2019 Afonso Mendes, Shashi Narayan, Sebastião Miranda, Zita Marinho, André F. T. Martins, Shay B. Cohen
Jointly extracting and compressing documents with summary state representations
published pages: , ISSN: , DOI:
Conference of the North American Chapter of the Association for Computational Linguistics (NAACL\'19) 2019-08-29
2019 Blondel, Mathieu; Martins, André F. T.; Niculae, Vlad
Learning Classifiers with Fenchel-Young Losses: Generalized Entropies, Margins, and Algorithms
published pages: , ISSN: , DOI:
Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS) 2019 2019-08-29
2019 Fabio Kepler, Jonay Trénous, Marcos Treviso, Miguel Vera, António Góis, M. Amin Farajian, António V. Lopes, André F. T. Martins
Unbabel\'s Participation in the WMT19 Translation Quality Estimation Shared Task
published pages: , ISSN: , DOI:
Conference on Machine Translation (WMT 2019) 2019-08-29
2019 Ben Peters, Vlad Niculae, André F. T. Martins
Sparse Sequence-to-Sequence Models
published pages: , ISSN: , DOI:
Annual Meeting of the Association for Computational Linguistics (ACL\'19) 2019-08-29
2019 Erick Fonseca, Lisa Yankovskaya, André F. T. Martins, Mark Fishel, Christian Federmann
Findings of the WMT 2019 Shared Tasks on Quality Estimation
published pages: , ISSN: , DOI:
Conference on Machine Translation (WMT 2019) 2019-08-29
2019 Pedro Henrique Martins, Zita Marinho, André F. T. Martins
Joint Learning of Named Entity Recognition and Entity Linking
published pages: , ISSN: , DOI:
Annual Meeting of the Association for Computational Linguistics (ACL\'19), Student Research Workshop 2019-08-29
2019 Tsvetomila Mihaylova, André F. T. Martins
Scheduled Sampling for Transformers
published pages: , ISSN: , DOI:
Annual Meeting of the Association for Computational Linguistics (ACL\'19), Student Research Workshop 2019-08-29
2019 Fábio Kepler, Jonay Trénous, Marcos Treviso, Miguel Vera, André F. T. Martins
Openkiwi: An open source framework for quality estimation
published pages: , ISSN: , DOI:
Annual Meeting of the Association for Computational Linguistics (ACL\'19), System Demonstrations 2019-08-29
2018 Vlad Niculae, Andre Martins, Mathieu Blondel, Claire Cardie
SparseMAP: Differentiable Sparse Structured Inference
published pages: 3796-3805, ISSN: , DOI:
Proceedings of the 35th International Conference on Machine Learning 80 2019-06-11
2018 Chaitanya Malaviya, Pedro Ferreira, André Martins
Sparse and Constrained Attention for Neural Machine Translation
published pages: , ISSN: , DOI:
Proceedings of the Annual Chapter of the Association for Computation Linguistics 2019-06-11
2018 Ben Peters, Vlad Niculae, André F. T. Martins
Interpretable Structure Induction via Sparse Attention
published pages: , ISSN: , DOI:
EMNLP Workshop for Analyzing and Interpreting Neural Networks for NLP 2019-04-14
2018 Sameen Maruf, Andre F. T. Martins, Gholamreza Haffari
Contextual Neural Model for Translating Bilingual Multi-Speaker Conversations
published pages: , ISSN: , DOI:
Conference for Machine Translation (WMT) 2019-04-14
2018 Vlad Niculae, André F. T. Martins and Claire Cardie
Towards Dynamic Computation Graphs via Sparse Latent Structure
published pages: , ISSN: , DOI:
Conference on Empirical Methods in Natural Language Processing 2019-04-14

Are you the coordinator (or a participant) of this project? Plaese send me more information about the "DEEPSPIN" 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 "DEEPSPIN" are provided by the European Opendata Portal: CORDIS opendata.

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

HyperBio (2019)

Vis-NIR Hyperspectral imaging for biomaterial quality control

Read More  

KineTic (2020)

New Reagents for Quantifying the Routing and Kinetics of T-cell Activation

Read More  

BALANCE (2019)

Mapping Dispersion Spectroscopically in Large Gas-Phase Molecular Ions

Read More