Zero-shot Multi-Domain Dialog State Tracking Using Descriptive Rules
- Autores
- Altszyler Lemcovich, Edgar Jaim; Brusco, Pablo; Basiou, Nikoletta; Byrnes, John; Vergyri, Dimitra
- Año de publicación
- 2020
- Idioma
- inglés
- Tipo de recurso
- artículo
- Estado
- versión publicada
- Descripción
- In this work, we present a framework for incorporating descriptive logical rules in state-of-the-art neural networks, enabling them to learn how to handle unseen labels without the introduction of any new training data. The rules are integrated into existing networks without modifying their architecture, through an additional term in the network’s loss function that penalizes states of the network that do not obey the designed rules.As a case of study, the framework is applied to an existing neuralbased Dialog State Tracker. Our experiments demonstrate that the inclusion of logical rules allows the prediction of unseen labels, without deteriorating the predictive capacity of the original system.
Fil: Altszyler Lemcovich, Edgar Jaim. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Computación; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Investigación en Ciencias de la Computación. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Investigación en Ciencias de la Computación; Argentina
Fil: Brusco, Pablo. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Investigación en Ciencias de la Computación. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Investigación en Ciencias de la Computación; Argentina. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Computación; Argentina
Fil: Basiou, Nikoletta. Sri International; Estados Unidos
Fil: Byrnes, John. Sri International; Estados Unidos
Fil: Vergyri, Dimitra. Sri International; Estados Unidos - Materia
-
ZERO-SHOT LEARNING
DIFFERENTIABLE LOGIC
NEURAL NETWORKS
DIALOG SYSTEMS - Nivel de accesibilidad
- acceso abierto
- Condiciones de uso
- https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
- Repositorio
- Institución
- Consejo Nacional de Investigaciones Científicas y Técnicas
- OAI Identificador
- oai:ri.conicet.gov.ar:11336/142699
Ver los metadatos del registro completo
id |
CONICETDig_bbc7f4ec01ed137692a226456c68a3ec |
---|---|
oai_identifier_str |
oai:ri.conicet.gov.ar:11336/142699 |
network_acronym_str |
CONICETDig |
repository_id_str |
3498 |
network_name_str |
CONICET Digital (CONICET) |
spelling |
Zero-shot Multi-Domain Dialog State Tracking Using Descriptive RulesAltszyler Lemcovich, Edgar JaimBrusco, PabloBasiou, NikolettaByrnes, JohnVergyri, DimitraZERO-SHOT LEARNINGDIFFERENTIABLE LOGICNEURAL NETWORKSDIALOG SYSTEMShttps://purl.org/becyt/ford/1.2https://purl.org/becyt/ford/1In this work, we present a framework for incorporating descriptive logical rules in state-of-the-art neural networks, enabling them to learn how to handle unseen labels without the introduction of any new training data. The rules are integrated into existing networks without modifying their architecture, through an additional term in the network’s loss function that penalizes states of the network that do not obey the designed rules.As a case of study, the framework is applied to an existing neuralbased Dialog State Tracker. Our experiments demonstrate that the inclusion of logical rules allows the prediction of unseen labels, without deteriorating the predictive capacity of the original system.Fil: Altszyler Lemcovich, Edgar Jaim. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Computación; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Investigación en Ciencias de la Computación. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Investigación en Ciencias de la Computación; ArgentinaFil: Brusco, Pablo. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Investigación en Ciencias de la Computación. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Investigación en Ciencias de la Computación; Argentina. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Computación; ArgentinaFil: Basiou, Nikoletta. Sri International; Estados UnidosFil: Byrnes, John. Sri International; Estados UnidosFil: Vergyri, Dimitra. Sri International; Estados UnidosCornell University2020-09info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/142699Altszyler Lemcovich, Edgar Jaim; Brusco, Pablo; Basiou, Nikoletta; Byrnes, John; Vergyri, Dimitra; Zero-shot Multi-Domain Dialog State Tracking Using Descriptive Rules; Cornell University; ArXiv; 2020; 9-2020; 1-42331-8422CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://arxiv.org/abs/2009.13275info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-29T10:11:21Zoai:ri.conicet.gov.ar:11336/142699instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-09-29 10:11:21.546CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse |
dc.title.none.fl_str_mv |
Zero-shot Multi-Domain Dialog State Tracking Using Descriptive Rules |
title |
Zero-shot Multi-Domain Dialog State Tracking Using Descriptive Rules |
spellingShingle |
Zero-shot Multi-Domain Dialog State Tracking Using Descriptive Rules Altszyler Lemcovich, Edgar Jaim ZERO-SHOT LEARNING DIFFERENTIABLE LOGIC NEURAL NETWORKS DIALOG SYSTEMS |
title_short |
Zero-shot Multi-Domain Dialog State Tracking Using Descriptive Rules |
title_full |
Zero-shot Multi-Domain Dialog State Tracking Using Descriptive Rules |
title_fullStr |
Zero-shot Multi-Domain Dialog State Tracking Using Descriptive Rules |
title_full_unstemmed |
Zero-shot Multi-Domain Dialog State Tracking Using Descriptive Rules |
title_sort |
Zero-shot Multi-Domain Dialog State Tracking Using Descriptive Rules |
dc.creator.none.fl_str_mv |
Altszyler Lemcovich, Edgar Jaim Brusco, Pablo Basiou, Nikoletta Byrnes, John Vergyri, Dimitra |
author |
Altszyler Lemcovich, Edgar Jaim |
author_facet |
Altszyler Lemcovich, Edgar Jaim Brusco, Pablo Basiou, Nikoletta Byrnes, John Vergyri, Dimitra |
author_role |
author |
author2 |
Brusco, Pablo Basiou, Nikoletta Byrnes, John Vergyri, Dimitra |
author2_role |
author author author author |
dc.subject.none.fl_str_mv |
ZERO-SHOT LEARNING DIFFERENTIABLE LOGIC NEURAL NETWORKS DIALOG SYSTEMS |
topic |
ZERO-SHOT LEARNING DIFFERENTIABLE LOGIC NEURAL NETWORKS DIALOG SYSTEMS |
purl_subject.fl_str_mv |
https://purl.org/becyt/ford/1.2 https://purl.org/becyt/ford/1 |
dc.description.none.fl_txt_mv |
In this work, we present a framework for incorporating descriptive logical rules in state-of-the-art neural networks, enabling them to learn how to handle unseen labels without the introduction of any new training data. The rules are integrated into existing networks without modifying their architecture, through an additional term in the network’s loss function that penalizes states of the network that do not obey the designed rules.As a case of study, the framework is applied to an existing neuralbased Dialog State Tracker. Our experiments demonstrate that the inclusion of logical rules allows the prediction of unseen labels, without deteriorating the predictive capacity of the original system. Fil: Altszyler Lemcovich, Edgar Jaim. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Computación; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Investigación en Ciencias de la Computación. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Investigación en Ciencias de la Computación; Argentina Fil: Brusco, Pablo. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Ciudad Universitaria. Instituto de Investigación en Ciencias de la Computación. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Instituto de Investigación en Ciencias de la Computación; Argentina. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales. Departamento de Computación; Argentina Fil: Basiou, Nikoletta. Sri International; Estados Unidos Fil: Byrnes, John. Sri International; Estados Unidos Fil: Vergyri, Dimitra. Sri International; Estados Unidos |
description |
In this work, we present a framework for incorporating descriptive logical rules in state-of-the-art neural networks, enabling them to learn how to handle unseen labels without the introduction of any new training data. The rules are integrated into existing networks without modifying their architecture, through an additional term in the network’s loss function that penalizes states of the network that do not obey the designed rules.As a case of study, the framework is applied to an existing neuralbased Dialog State Tracker. Our experiments demonstrate that the inclusion of logical rules allows the prediction of unseen labels, without deteriorating the predictive capacity of the original system. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020-09 |
dc.type.none.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion http://purl.org/coar/resource_type/c_6501 info:ar-repo/semantics/articulo |
format |
article |
status_str |
publishedVersion |
dc.identifier.none.fl_str_mv |
http://hdl.handle.net/11336/142699 Altszyler Lemcovich, Edgar Jaim; Brusco, Pablo; Basiou, Nikoletta; Byrnes, John; Vergyri, Dimitra; Zero-shot Multi-Domain Dialog State Tracking Using Descriptive Rules; Cornell University; ArXiv; 2020; 9-2020; 1-4 2331-8422 CONICET Digital CONICET |
url |
http://hdl.handle.net/11336/142699 |
identifier_str_mv |
Altszyler Lemcovich, Edgar Jaim; Brusco, Pablo; Basiou, Nikoletta; Byrnes, John; Vergyri, Dimitra; Zero-shot Multi-Domain Dialog State Tracking Using Descriptive Rules; Cornell University; ArXiv; 2020; 9-2020; 1-4 2331-8422 CONICET Digital CONICET |
dc.language.none.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
info:eu-repo/semantics/altIdentifier/url/https://arxiv.org/abs/2009.13275 |
dc.rights.none.fl_str_mv |
info:eu-repo/semantics/openAccess https://creativecommons.org/licenses/by-nc-sa/2.5/ar/ |
eu_rights_str_mv |
openAccess |
rights_invalid_str_mv |
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/ |
dc.format.none.fl_str_mv |
application/pdf application/pdf |
dc.publisher.none.fl_str_mv |
Cornell University |
publisher.none.fl_str_mv |
Cornell University |
dc.source.none.fl_str_mv |
reponame:CONICET Digital (CONICET) instname:Consejo Nacional de Investigaciones Científicas y Técnicas |
reponame_str |
CONICET Digital (CONICET) |
collection |
CONICET Digital (CONICET) |
instname_str |
Consejo Nacional de Investigaciones Científicas y Técnicas |
repository.name.fl_str_mv |
CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas |
repository.mail.fl_str_mv |
dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar |
_version_ |
1844614011336785920 |
score |
13.070432 |