Opendata, web and dolomites

INTERACT SIGNED

Interactive Machine Learning for Compositional Models of Natural Language

Total Cost €

0

EC-Contrib. €

0

Partnership

0

Views

0

Project "INTERACT" data sheet

The following table provides information about the project.

Coordinator
UNIVERSITAT POLITECNICA DE CATALUNYA 

Organization address
address: CALLE JORDI GIRONA 31
city: BARCELONA
postcode: 8034
website: www.upc.edu

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 Spain [ES]
 Total cost 1˙499˙375 €
 EC max contribution 1˙499˙375 € (100%)
 Programme 1. H2020-EU.1.1. (EXCELLENT SCIENCE - European Research Council (ERC))
 Code Call ERC-2019-STG
 Funding Scheme ERC-STG
 Starting year 2020
 Duration (year-month-day) from 2020-03-01   to  2025-02-28

 Partnership

Take a look of project's partnership.

# participants  country  role  EC contrib. [€] 
1    UNIVERSITAT POLITECNICA DE CATALUNYA ES (BARCELONA) coordinator 1˙499˙375.00

Map

 Project objective

INTERACT will develop new Interactive Learning Algorithms (ILA), motivated by applications in Natural Language Understanding (NLU). The main assumptions behind supervised approaches are unrealistic because most NLU applications have unique information needs, and large collections of annotated data are necessary to achieve good performance. INTERACT follows a collaborative machine learning paradigm that breaks the distinction between annotation and training. We focus on compositional latent-state models (CLSMs) because natural language is rich, complex and compositional. To reduce the amount of human feedback necessary for learning CLSMs we must eliminate annotation redundancy. We argue that to achieve this in the context of CLSMs we must combine: (1) An optimal human feedback strategy, with (2) inducing a latent structure of parts in the compositional domain. Annotation effort will be minimized because the method will only request representative feedback from each latent class. INTERACT marries representation learning (i.e. of parts) and active learning for CLSMs.

Our approach goes beyond classical active learning where the ILA asks labels for samples chosen from a pool of unlabeled data. We empower the ILA with the ability to ask for labels for any complete or partial structure in the domain, i.e. the ILA will be able to generate samples.

We work under the framework of spectral learning of weighted automata and grammars and use ideas from query learning. A key idea is reducing the problem of interactive learning of CLSMs to a form of interactive low-rank matrix completion. Our concrete goals are: (1) Develop ILAs for CLSMs based on spectral learning techniques; and (2) Investigate optimal strategies to leverage human feedback, taking into account what is optimal for the ILA and what is easy for the teacher.

We will experiment with NLU tasks of increasing complexity, from sequence and tree classification to parsing problems where the outputs are trees.

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

SuperH (2019)

Discovery and Characterization of Hydrogen-Based High-Temperature Superconductors

Read More  

TALNET (2020)

Transparent Aluminium Networks

Read More