Grant: Discovery Grants Program - Individual
University of Ottawa
$17,000.00
Natural Language Generation and Analysis
FY 2016-17
Summary
Recently, there was a lot of progress in the research area of Natural Language Processing, leading to many commercial applications. Tools such as grammar correctors, machine translators, and information extraction systems can now assist people and help saving time and costs. They are taking us one step closer to the goals of Artificial Intelligence. Tools such as automatic speech recognizers and intelligent tutoring systems also lead to progress in Human-Computer Interaction. The sub-area of Natural Language Generation has seen a slower progress, but automatic text generation started to be used in applications, including generating instructions, health care reports, text messages for interactive simulations (for training purposes or for entertainment), etc. The long term objective of the proposed research program is to facilitate further advances in these directions and to fill in the gap in the area of Natural Language Generation. The proposed short-term objectives are to develop new methods for automatic text generation and for text analysis and classification, by using the results of the analysis stage to guide the generation stage. The novelty of the proposed approach consists in the ways the results and the insights from the text analysis stage will be used in order to develop new methods for text generation. I will focus on several applications for English and French, for which I did some preliminary work in current and past projects: classification of texts by the emotion expressed (such as happiness, anger, fear, surprise, disgust, and sadness) and generation of texts that express a desired emotion; classification of texts by style and generation of texts with a particular style (such as formal or informal); classification of medical texts and generation of texts for medical reports; intelligent text retrieval and database access using keywords or natural language sentences, and generation of natural language descriptions for existing database reports. I anticipate that the new methods and the proposed applications will advance the state-of-the-art in research, while also allowing for technology transfer into industrial applications.
Program
Discovery Grants Program - Individual
Recipient
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
298150-2012
Name nom
Inkpen, Diana
Department département
Electrical Engineering and Computer Science , School of
Organization id
28
Institution établissement
University of Ottawa
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2016
Competition year année de concours
2012
Award amount
17000
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
801
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Computer software
Area of application fr
Logiciel
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
5
Nb partie
5
Application title
Natural Language Generation and Analysis
Keyword
NSERC
Application summary
Recently, there was a lot of progress in the research area of Natural Language Processing, leading to many commercial applications. Tools such as grammar correctors, machine translators, and information extraction systems can now assist people and help saving time and costs. They are taking us one step closer to the goals of Artificial Intelligence. Tools such as automatic speech recognizers and intelligent tutoring systems also lead to progress in Human-Computer Interaction. The sub-area of Natural Language Generation has seen a slower progress, but automatic text generation started to be used in applications, including generating instructions, health care reports, text messages for interactive simulations (for training purposes or for entertainment), etc. The long term objective of the proposed research program is to facilitate further advances in these directions and to fill in the gap in the area of Natural Language Generation. The proposed short-term objectives are to develop new methods for automatic text generation and for text analysis and classification, by using the results of the analysis stage to guide the generation stage. The novelty of the proposed approach consists in the ways the results and the insights from the text analysis stage will be used in order to develop new methods for text generation. I will focus on several applications for English and French, for which I did some preliminary work in current and past projects: classification of texts by the emotion expressed (such as happiness, anger, fear, surprise, disgust, and sadness) and generation of texts that express a desired emotion; classification of texts by style and generation of texts with a particular style (such as formal or informal); classification of medical texts and generation of texts for medical reports; intelligent text retrieval and database access using keywords or natural language sentences, and generation of natural language descriptions for existing database reports. I anticipate that the new methods and the proposed applications will advance the state-of-the-art in research, while also allowing for technology transfer into industrial applications.