Grant: Engage Grants Program
University of Ottawa
$25,000.00
Automatic extraction of todo items from notes
FY 2012-13
Summary
With the widespread adoption of tablet technology, led by Apple's iPad device, more and more people are moving from the traditional method of note taking using pen and paper to electronic note taking in business and academia. The value of electronic note taking is that it allows the note taker to upload their notes to a central storage facility such as Evernote or Dropbox and thereby enables them to share, search and access their notes from anywhere at any time. While this functionality is extremely powerful, many users of electronic notes do not become full adopters of the technology because the note repositories are often ""out of sight and out of mind"" without the immediacy of paper. We propose to develop methods for automatically parsing electronic notes stored in the cloud based system, understanding the intent of certain portions of these notes and forwarding them to the appropriate web service. For instance, if the system detects that a user has entered the text ""Remember to buy milk"" in their notes, that portion of text will be automatically entered into the user's defined shopping list service which might be a service such as Google Tasks, Wunderlist or ReQall. The proposed project will develop a prototype that detects ""to do"" items and forwards them to a single web service.
The methods that we will design will work in two steps. Automatic text classification methods will be used to classify notes as containing a ""to do"" item or not. Then, information extraction techniques will be used to extract the actual ""to do"" item. For both steps, we will evaluate the correctness of the results and improve the methods as needed, on a development dataset. At the end, a test set will be used for the final evaluation. Our industrial partner, Tindr solutions Inc, is planning to commercialize the result of this collaboration into a software application that will revolutionize the electronic note-taking industry.
Program
Engage Grants Program
Recipient
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
430863-2012
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
2012
Competition year année de concours
2012
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
Automatic extraction of todo items from notes
Keyword
NSERC
Application summary
With the widespread adoption of tablet technology, led by Apple's iPad device, more and more people are moving from the traditional method of note taking using pen and paper to electronic note taking in business and academia. The value of electronic note taking is that it allows the note taker to upload their notes to a central storage facility such as Evernote or Dropbox and thereby enables them to share, search and access their notes from anywhere at any time. While this functionality is extremely powerful, many users of electronic notes do not become full adopters of the technology because the note repositories are often ""out of sight and out of mind"" without the immediacy of paper. We propose to develop methods for automatically parsing electronic notes stored in the cloud based system, understanding the intent of certain portions of these notes and forwarding them to the appropriate web service. For instance, if the system detects that a user has entered the text ""Remember to buy milk"" in their notes, that portion of text will be automatically entered into the user's defined shopping list service which might be a service such as Google Tasks, Wunderlist or ReQall. The proposed project will develop a prototype that detects ""to do"" items and forwards them to a single web service.
The methods that we will design will work in two steps. Automatic text classification methods will be used to classify notes as containing a ""to do"" item or not. Then, information extraction techniques will be used to extract the actual ""to do"" item. For both steps, we will evaluate the correctness of the results and improve the methods as needed, on a development dataset. At the end, a test set will be used for the final evaluation. Our industrial partner, Tindr solutions Inc, is planning to commercialize the result of this collaboration into a software application that will revolutionize the electronic note-taking industry.