Grant: Engage Grants Program
McGill University
$25,000.00
Learning Frame Semantics with Deep Neural Networks for the Winograd Schema Challenge
EF 2016-17
Résumé
A limitation of current dialogue systems and virtual personal assistant apps is that they can only handle specificapplication domains following a more or less standard frame (a.k.a., script or scenario). Maluuba is a Canadiancompany that is interested in overcoming this limitation by developing techniques for performing commonsense reasoning. Common sense reasoning involves understanding the typical characteristics, motivations andintents of people within a certain frame. In this project, we aim to investigate deep learning techniques forlearning frame representations from large corpora, which we will then apply to a task in common sensereasoning called the Winograd Schema Challenge (WSC). This task involves identifying entities that are beingdiscussed in certain contexts. We will create an enhanced dataset of WSC questions, with which we will train adeep learning model for predicting WSC answers. The outcome of this research will be of use in Maluuba'sefforts to develop more flexible and naturalistic conversational agents.
Programme
Engage Grants Program
Bénéficiaire
Emplacement
Quebec, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
502340-2016
Name nom
Cheung, Jackie
Department département
Computer Science, School of
Organization id
61
Institution établissement
McGill University
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2016
Competition year année de concours
2016
Award amount
25000
Program id
EGP
Program name en
Engage Grants Program
Program name fr
Programme de subventions d'engagement partenariat
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
1552
Committee name en
Quebec Internal Decision Committee
Committee name fr
Comité de décision interne pour le Québec
Area of application code
802
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Information systems and technology
Area of application fr
Systèmes d'information et technologie de l'information
Research subject code
2801
Research subject group en
Artificial intelligence
Research subject group fr
Intelligence artificielle
Research subject en
Natural language and speech understanding
Research subject fr
Langage naturel et reconnaissance de la parole
Partie
1
Nb partie
1
Application title
Learning Frame Semantics with Deep Neural Networks for the Winograd Schema Challenge
Keyword
NSERC
Application summary
A limitation of current dialogue systems and virtual personal assistant apps is that they can only handle specificapplication domains following a more or less standard frame (a.k.a., script or scenario). Maluuba is a Canadiancompany that is interested in overcoming this limitation by developing techniques for performing commonsense reasoning. Common sense reasoning involves understanding the typical characteristics, motivations andintents of people within a certain frame. In this project, we aim to investigate deep learning techniques forlearning frame representations from large corpora, which we will then apply to a task in common sensereasoning called the Winograd Schema Challenge (WSC). This task involves identifying entities that are beingdiscussed in certain contexts. We will create an enhanced dataset of WSC questions, with which we will train adeep learning model for predicting WSC answers. The outcome of this research will be of use in Maluuba'sefforts to develop more flexible and naturalistic conversational agents.