Grant: Collaborative Research and Development Grants
Centre de recherche informatique de Montréal
$61,760.00
Toward a second generation of an automatic product coding system
FY 2012-13
Summary
The company 3CE offers to their clients, a semi-automatic classification system, which leads users with a minimal number of questions, from their product description to the appropriate HS (Harmonized System) code. For example, from ""ceramic tiles"", the system will ask whether it is a ""constructional good"" or a ""floor covering"" as these would lead to two slightly different codes (69.03 or 69.05). Or from ""chicken"" it will ask whether it is alive or not, and if it is alive how much does it weigh, as these factors will influence the resulting code. 3CE's online system contains a nice user interface and is already very helpful to importers, but 3CE is looking further to expand their business and continue growing, and for doing so, in this collaborative research project, they wish to address two challenges.
First, some importers wish for the semi-automatic interactive system to become a fully automatic batch processing system. But for 3CE, if the human is taken out of the loop, their classification system must become even smarter at analyzing product description and inferring information leading to a non-ambiguous code from a probably ambiguous description. Exporters write product descriptions such as ""frame wood photo pc bamboo"", ""candy gummi choice l'il bears"", or ""sharpener pencil sport ball"". This becomes a very difficult problem requiring investigation into many different natural language processing tasks (synonym finding, abbreviation resolution, complex noun parsing, etc).
Second, 3CE is often being asked if they can categorize items into other systems than the HS. To do so, 3CE must investigate a way of encoding their ""world ontology"" (how people describe products) and the HS as separate entities with a linking engine between them, rather then the present system which is more or less integrated. In this collaborative effort, we will look at research in ontology development and mostly ontology alignment. Those are major challenges for researchers interested in the semantic web and linked data. We will explore these areas with product classification in mind as the end goal.
Program
Collaborative Research and Development Grants
Location
Quebec, Canada
Recipient Type
Not-for-profit organization or charity
Type
Grant
Source
NSERC's Awards Data
As published
Application id
417968-2011
Name nom
Barrière, Caroline
Department département
Recherche et Développement
Organization id
71
Institution établissement
Centre de recherche informatique de Montréal
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2012
Competition year année de concours
2011
Award amount
61760
Program id
CRDPJ
Program name en
Collaborative Research and Development Grants
Program name fr
Subventions de recherche et développement coopérative
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
96
Committee name en
RPP Internal Decision Cttee
Committee name fr
Cté de décision interne - PPR
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
2700
Research subject group en
Information technology
Research subject group fr
Technologie de l'information
Research subject en
Information technology
Research subject fr
Technologie de l'information
Partie
2
Nb partie
3
Application title
Toward a second generation of an automatic product coding system
Keyword
NSERC
Application summary
The company 3CE offers to their clients, a semi-automatic classification system, which leads users with a minimal number of questions, from their product description to the appropriate HS (Harmonized System) code. For example, from ""ceramic tiles"", the system will ask whether it is a ""constructional good"" or a ""floor covering"" as these would lead to two slightly different codes (69.03 or 69.05). Or from ""chicken"" it will ask whether it is alive or not, and if it is alive how much does it weigh, as these factors will influence the resulting code. 3CE's online system contains a nice user interface and is already very helpful to importers, but 3CE is looking further to expand their business and continue growing, and for doing so, in this collaborative research project, they wish to address two challenges.
First, some importers wish for the semi-automatic interactive system to become a fully automatic batch processing system. But for 3CE, if the human is taken out of the loop, their classification system must become even smarter at analyzing product description and inferring information leading to a non-ambiguous code from a probably ambiguous description. Exporters write product descriptions such as ""frame wood photo pc bamboo"", ""candy gummi choice l'il bears"", or ""sharpener pencil sport ball"". This becomes a very difficult problem requiring investigation into many different natural language processing tasks (synonym finding, abbreviation resolution, complex noun parsing, etc).
Second, 3CE is often being asked if they can categorize items into other systems than the HS. To do so, 3CE must investigate a way of encoding their ""world ontology"" (how people describe products) and the HS as separate entities with a linking engine between them, rather then the present system which is more or less integrated. In this collaborative effort, we will look at research in ontology development and mostly ontology alignment. Those are major challenges for researchers interested in the semantic web and linked data. We will explore these areas with product classification in mind as the end goal.
