Hola,
¿eres nuevo aquí?

Regístrate gratis y conecta tu empresa con financiación pública, partners y proyectos.

Tengo cuenta

Regístrate

Ver video

INTERACT

Financiado

Interactive Machine Learning for Compositional Models of Natural Language

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 ha... ver más

28/02/2026

UPC

1M€

Presupuesto del proyecto: 1M€

Líder del proyecto

Universidad Politécnica de Cataluña No se ha especificado una descripción o un objeto social para esta compañía.

Total investigadores 9

Ver 2 Participantes

Financiación concedida El organismo H2020 notifico la concesión del proyecto el día 2019-11-28

ERC-2019-STG: ERC Starting Grant

I+D

Cerrada hace 6 años

0% 100% 100%

2 Participantes

UPC

1.50M€ | Lider

FNX INDUSTRIAL

1.97M€ | Participante

Conecta tu I+D

¿Tienes un proyecto y buscas un partner? Gracias a nuestro motor inteligente podemos recomendarte los mejores socios y ponerte en contacto con ellos. Te lo explicamos en este video

Duración del proyecto: 75 meses Fecha Inicio: 2019-11-28
Fecha Fin: 2026-02-28

Líder del proyecto

Universidad Politécnica de Cataluña No se ha especificado una descripción o un objeto social para esta compañía.

Total investigadores 9

Presupuesto del proyecto 1M€

Descripción del proyecto 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.

Conecta tu I+D

Entra hoy

¿Olvidé mi contraseña?

Financiación

Empresas

CTIs/Universidades

Proyectos

Investigadores