Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Engage Grants Program

University of Ottawa

$25,000.00

Natural language descriptions for business intelligence

FY 2010-11

Summary
NexJ Systems, a developer of enterprise customer relationship software, is interested in enhancing its business intelligence (BI) products with natural language processing (NLP) technologies. One function of NexJ's BI software allows users to build queries/filters that allow them to extract important information from the system. These queries are expressed in a computer language (SQL style). We propose to generate natural language description for these filters. Expressing a computer language query in natural languages is a challenge for standard programming approaches. The problem is particularly hard to solve when multiple spoken languages are considered. We will start with English and French, and keep the methodology open for adding new languages. We propose to use natural language generation techniques to automatically produce these natural language descriptions. We will focus on sentence realization and grammar modules for verb-subject agreement, pronouns, etc. We will add aggregation modules in order to summarize information. As well as this initial problem, a number of other opportunities for NLP to improve the software have been identified. It is hoped that this initial project will be the first of a number of collaborations of NexJ with the University of Ottawa, and with the NLP academic community in general.
Program
Engage Grants Program
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
401982-2010
Name nom
Inkpen, Diana
Department département
Information Technology and Engineering, 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
2010
Competition year année de concours
2010
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
1553
Committee name en
Ontario Internal Decision Committee
Committee name fr
Comité de décision interne pour l'Ontario
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
1
Nb partie
1
Application title
Natural language descriptions for business intelligence
Keyword
NSERC
Application summary
NexJ Systems, a developer of enterprise customer relationship software, is interested in enhancing its business intelligence (BI) products with natural language processing (NLP) technologies. One function of NexJ's BI software allows users to build queries/filters that allow them to extract important information from the system. These queries are expressed in a computer language (SQL style). We propose to generate natural language description for these filters. Expressing a computer language query in natural languages is a challenge for standard programming approaches. The problem is particularly hard to solve when multiple spoken languages are considered. We will start with English and French, and keep the methodology open for adding new languages. We propose to use natural language generation techniques to automatically produce these natural language descriptions. We will focus on sentence realization and grammar modules for verb-subject agreement, pronouns, etc. We will add aggregation modules in order to summarize information. As well as this initial problem, a number of other opportunities for NLP to improve the software have been identified. It is hoped that this initial project will be the first of a number of collaborations of NexJ with the University of Ottawa, and with the NLP academic community in general.