Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Discovery Grants Program - Individual

Université de Montréal

$29,000.00

Interactive Natural Language Generation

EF 2015-16

Résumé
<span style=""line-height: 1.5em;"">This research focuses on Natural Language Generation (NLG) but from a very specific viewpoint: Natural Language Generation as an Interactive (i.e. machine mediated) process. Interactive Natural Language Generation (INLG) is an original take on NLG in as it integrates cognitive aspects of text production which are generally neglected in fully automated text production. Since language production is to a large extent knowledge transfer, we deal not only with language as such (conversion of meanings into form) but also with knowledge, its structure, representation, and use (access, transformation) .  <span style=""line-height: 1.5em;""><span style=""line-height: 1.5em;"">  <span style=""line-height: 1.5em;"">Language generation has been described in depth from two points of view: Levelt, a psychologist, describes the mental processes, while Reiter and Dale, two computational linguists, explain how to build generators. Their focus is on fully automated text generation. We focus here on language production with the help of a machine. Put differenly, we take a hybrid approach drawing on knowledge from psycholinguistics and language engineering, relying in addition on the human factor : currently avaialable knowledge cognitive constraints (memory, attention), capacities of reasoning and information processing and the learning of the skills of speaking and writing. <span style=""line-height: 1.5em;""><span style=""line-height: 1.5em;"">  <span style=""line-height: 1.5em;"">This research program, which involves 2 PhDs, 4 MScs and a postdoctoral fellow, will work towards solutions of yet unsolved problems by referring to existing theoretical work and by offering practical web-based applications. While each task is independent it explores and illustrates a specific facet of our overall framework in order to allow for the emulation and cooperation between students. <span style=""line-height: 1.5em;""><span style=""line-height: 1.5em;"">  <span style=""line-height: 1.5em;"">The originality of this work with respect to existing work lies in the fact that we include humans and the human factor (psychological constraints : memory, attention) into the process. While benefitting from the final product (word, sentence, text) they also contribute to its building. In addition, we take into account the knowledge accumulated in different fields: cognitive psychology, natural language generation, natural language processing. Our goals is to illustrate how current technology can be used to assist humans in producing language, or in acquiring this skill in a foreign language. While focusing on the building tools we will also highlight the factors that need to be taken into account to enable people to generate language with the help of computers.  <span style=""line-height: 1.5em;""><span style=""line-height: 1.5em;"">  <span style=""line-height: 1.5em;"">In order to reach our goal, we will draw on the experience (three decades) accumulated while working natural language generation in related projects as well as on the preliminary explorations and prototypes developed within our past NSERC discovery grants.
Programme
Discovery Grants Program - Individual
Emplacement
Quebec, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
RGPIN-2015-05164
Name nom
Lapalme, Guy
Department département
Informatique et recherche opérationnelle - Informatique et recherche opérationne
Organization id
63
Institution établissement
Université de Montréal
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2015
Competition year année de concours
2015
Award amount
29000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
Discovery grants programs
Group fr
Programmes de subventions à la découverte
Committee code
1507
Committee name en
Computer Science
Committee name fr
Sciences informatiques
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
Interactive Natural Language Generation
Keyword
NSERC
Application summary
<div><span style=""line-height: 1.5em;"">This research focuses on Natural Language Generation (NLG) but from a very specific viewpoint: Natural Language Generation as an Interactive (i.e. machine mediated) process. Interactive Natural Language Generation (INLG) is an original take on NLG in as it integrates cognitive aspects of text production which are generally neglected in fully automated text production. Since language production is to a large extent knowledge transfer, we deal not only with language as such (conversion of meanings into form) but also with knowledge, its structure, representation, and use (access, transformation) . </span></div> <div><span style=""line-height: 1.5em;""></span><span style=""line-height: 1.5em;""> </span></div> <div><span style=""line-height: 1.5em;"">Language generation has been described in depth from two points of view: Levelt, a psychologist, describes the mental processes, while Reiter and Dale, two computational linguists, explain how to build generators. Their focus is on fully automated text generation. We focus here on language production with the help of a machine. Put differenly, we take a hybrid approach drawing on knowledge from psycholinguistics and language engineering, relying in addition on the human factor : currently avaialable knowledge cognitive constraints (memory, attention), capacities of reasoning and information processing and the learning of the skills of speaking and writing.</span></div> <div><span style=""line-height: 1.5em;""></span><span style=""line-height: 1.5em;""> </span></div> <div><span style=""line-height: 1.5em;"">This research program, which involves 2 PhDs, 4 MScs and a postdoctoral fellow, will work towards solutions of yet unsolved problems by referring to existing theoretical work and by offering practical web-based applications. While each task is independent it explores and illustrates a specific facet of our overall framework in order to allow for the emulation and cooperation between students.</span></div> <div><span style=""line-height: 1.5em;""></span><span style=""line-height: 1.5em;""> </span></div> <div><span style=""line-height: 1.5em;"">The originality of this work with respect to existing work lies in the fact that we include humans and the human factor (psychological constraints : memory, attention) into the process. While benefitting from the final product (word, sentence, text) they also contribute to its building. In addition, we take into account the knowledge accumulated in different fields: cognitive psychology, natural language generation, natural language processing. Our goals is to illustrate how current technology can be used to assist humans in producing language, or in acquiring this skill in a foreign language. While focusing on the building tools we will also highlight the factors that need to be taken into account to enable people to generate language with the help of computers. </span></div> <div><span style=""line-height: 1.5em;""></span><span style=""line-height: 1.5em;""> </span></div> <div><span style=""line-height: 1.5em;"">In order to reach our goal, we will draw on the experience (three decades) accumulated while working natural language generation in related projects as well as on the preliminary explorations and prototypes developed within our past NSERC discovery grants.</span></div>