Grant: Engage Grants Program
Dalhousie University
$25,000.00
Resume job matching using google n-grams
FY 2014-15
Summary
Given a job description, the task of an employer is to rank job candidates from a set of resumes to create a shortlist for interview. The ultimate goal of this project is to accelerate and improve employers' ability to find themost qualified candidates for a position by reducing human effort in the resume evaluation process. Such anautomated system can also be helpful for potential job seekers in finding job openings that best match theirqualifications. Interview Rocket is an online job candidate pre-screening tool, using captured video responses.Its objective is to save time arranging appointments and managing large volumes of candidates. A decisionsupport method solely based on text (i.e., resumes and job description) would complement the video capturecomponent, and would add new capabilities to the current version of the tool. The objective of the project is thedesign and implementation of a resume-job matching algorithm based on the text similarity approach proposedin (Islam et al., 2012) considering the similarity of the job description with each of the resumes. The textsimilarity approach that we aim to use is based on word relatedness using the Google tri-gram corpus (Brantsand Franz, 2006), consisting of all consecutive triples of words that appear frequently enough on the Web. Themain idea of the text similarity approach is to find for each word in the job description, some most significantmatches at the word level based on the word relatedness scores, in the resume text. One of the main advantagesof using n-gram based method is its language independence.
Program
Engage Grants Program
Recipient
Location
Nova Scotia, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
462736-2014
Name nom
Milios, Evangelos
Department département
Computer Science, Faculty of
Organization id
79
Institution établissement
Dalhousie University
Province en
Nova Scotia
Province fr
Nouvelle-Écosse
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2014
Competition year année de concours
2014
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
1551
Committee name en
Atlantic Internal Decision Committee
Committee name fr
Comité de décision interne pour l'Atlantique
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
1
Nb partie
1
Application title
Resume job matching using google n-grams
Keyword
NSERC
Application summary
Given a job description, the task of an employer is to rank job candidates from a set of resumes to create a shortlist for interview. The ultimate goal of this project is to accelerate and improve employers' ability to find themost qualified candidates for a position by reducing human effort in the resume evaluation process. Such anautomated system can also be helpful for potential job seekers in finding job openings that best match theirqualifications. Interview Rocket is an online job candidate pre-screening tool, using captured video responses.Its objective is to save time arranging appointments and managing large volumes of candidates. A decisionsupport method solely based on text (i.e., resumes and job description) would complement the video capturecomponent, and would add new capabilities to the current version of the tool. The objective of the project is thedesign and implementation of a resume-job matching algorithm based on the text similarity approach proposedin (Islam et al., 2012) considering the similarity of the job description with each of the resumes. The textsimilarity approach that we aim to use is based on word relatedness using the Google tri-gram corpus (Brantsand Franz, 2006), consisting of all consecutive triples of words that appear frequently enough on the Web. Themain idea of the text similarity approach is to find for each word in the job description, some most significantmatches at the word level based on the word relatedness scores, in the resume text. One of the main advantagesof using n-gram based method is its language independence.