Opendata, web and dolomites

CALCULUS SIGNED

Commonsense and Anticipation enriched Learning of Continuous representations sUpporting Language UnderStanding

Total Cost €

0

EC-Contrib. €

0

Partnership

0

Views

0

 CALCULUS project word cloud

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

world    events    data    neural    continuous    reusable    intelligence    processed    learning    inference    experiences    social    parsing    geometric    trained    interdisciplinary    manually    event    perceptual    implicit    networks    structure    successful    limited    written    machine    spatial    spaces    training    happening    pi    commonsense    narrative    mentioned    relying    probabilistic    natural    ideas    acquired    left    grounded    retrieval    scientific    expertise    models    symbolic    temporal    language    inspired    requiring    perform    settings    innovative    frames    stories    texts    virtual    embodying    representations    combine    annotated    situations    capability    supporting    explicit    nlu    anticipatory    paradigms    realization    latent    grammatical    demonstrator    artificial    days    engage    metric    translates    inferring    economic    time    visual    powerful    anticipate    structures    efficient    joint    bayesian    humans    imagine    calculus   

Project "CALCULUS" data sheet

The following table provides information about the project.

Coordinator
KATHOLIEKE UNIVERSITEIT LEUVEN 

Organization address
address: OUDE MARKT 13
city: LEUVEN
postcode: 3000
website: www.kuleuven.be

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 Belgium [BE]
 Total cost 2˙227˙500 €
 EC max contribution 2˙227˙500 € (100%)
 Programme 1. H2020-EU.1.1. (EXCELLENT SCIENCE - European Research Council (ERC))
 Code Call ERC-2017-ADG
 Funding Scheme ERC-ADG
 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    KATHOLIEKE UNIVERSITEIT LEUVEN BE (LEUVEN) coordinator 2˙227˙500.00

Map

 Project objective

Natural language understanding (NLU) by the machine is of large scientific, economic and social value. Humans perform the NLU task in an efficient way by relying on their capability to imagine or anticipate situations. They engage commonsense and world knowledge that is often acquired through perceptual experiences to make explicit what is left implicit in language. Inspired by these characteristics CALCULUS will design, implement and evaluate innovative paradigms supporting NLU, where it will combine old but powerful ideas for language understanding from the early days of artificial intelligence with new approaches from machine learning. The project focuses on the effective learning of anticipatory, continuous, non-symbolic representations of event frames and narrative structures of events that are trained on language and visual data. The grammatical structure of language is grounded in the geometric structure of visual data while embodying aspects of commonsense and world knowledge. The reusable representations are evaluated in a selection of NLU tasks requiring efficient real-time retrieval of the representations and parsing of the targeted written texts. Finally, we will evaluate the inference potential of the anticipatory representations in situations not seen in the training data and when inferring spatial and temporal information in metric real world spaces that is not mentioned in the processed language. The machine learning methods focus on learning latent variable models relying on Bayesian probabilistic models and neural networks and focus on settings with limited training data that are manually annotated. The best models will be integrated in a demonstrator that translates the language of stories to events happening in a 3-D virtual world. The PI has interdisciplinary expertise in natural language processing, joint processing of language and visual data, information retrieval and machine learning needed for the successful realization of the project.

 Publications

year authors and title journal last update
List of publications.
2019 Cornille, Nathan & Moens, Marie-Francine
Improving Language Understanding in Machines through Anticipation. In. 2019
published pages: , ISSN: , DOI:
3rd Human Brain Project Curriculum Workshop on Cognitive Systems 2020-04-24
2020 Cornille, Nathan & Moens, Marie-Francine
Improving Representation Learning with Pervasive Internal Regression (PIR)
published pages: , ISSN: , DOI:
Proceedings of the CSHL Meeting: From Neuroscience to Artificially Intelligent Systems (NAISys) 2020-04-24
2019 Spinks, Graham, Cartuyvels, Ruben & Moens, Marie-Francine
Learning Grammar in Confined Worlds. In ). 2020
published pages: , ISSN: , DOI:
Proceedings of the International Workshop on Spoken Dialog System Technology (IWSDS 2020 2020-04-24
2019 Artuur Leeuwenberg, Marie-Francine Moens
A Survey on Temporal Reasoning for Temporal Information Extraction from Text
published pages: 341-380, ISSN: 1076-9757, DOI: 10.1613/jair.1.11727
Journal of Artificial Intelligence Research 66 2020-04-24
2020 Deruyttere, Thierry & Moens, Marie-Francine
Giving Commands to a Self-driving Car: A Multimodal Reasoner for Visual Grounding
published pages: , ISSN: , DOI:
Proceedings of AAAI 2020 Reasoning for Complex Question Answering Workshop 2020-04-24
2019 Graham Spinks, Marie-Francine Moens
Justifying diagnosis decisions by deep neural networks
published pages: 103248, ISSN: 1532-0464, DOI: 10.1016/j.jbi.2019.103248
Journal of Biomedical Informatics 96 2020-04-24

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

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

NanoPD_P (2020)

High throughput multiplexed trace-analyte screening for diagnostics applications

Read More  

FICOMOL (2019)

Field Control of Cold Molecular Collisions

Read More  

FuncMAB (2019)

High-throughput single-cell phenotypic analysis of functional antibody repertoires

Read More