Skills prediction based on multi-label resume classification using CNN with model predictions explanation
- PDF / 2,320,963 Bytes
- 19 Pages / 595.276 x 790.866 pts Page_size
- 72 Downloads / 201 Views
(0123456789().,-volV)(0123456789().,-volV)
ORIGINAL ARTICLE
Skills prediction based on multi-label resume classification using CNN with model predictions explanation Kameni Florentin Flambeau Jiechieu1,2
•
Norbert Tsopze1,2
Received: 6 February 2020 / Accepted: 18 August 2020 Ó Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract Skills extraction is a critical task when creating job recommender systems. It is also useful for building skills profiles and skills knowledge bases for organizations. The aim of skills extraction is to identify the skills expressed in documents such as resumes or job postings. Several methods have been proposed to tackle this problem. These methods already perform well when it comes to extracting explicitly mentioned skills from resumes. But skills have different levels of abstraction: high-level skills can be determined by low-level ones. Instead of just extracting skill-related terms, we propose a multilabel classification architecture model based on convolutional neural networks to predict high-level skills from resumes even if they are not explicitly mentioned in these resumes. Experiments carried out on a set of anonymous IT resumes collected from the Internet have shown the effectiveness of our method reaching 98.79% of recall and 91.34% of precision. In addition, features (terms) detected by convolutional filters are projected on the input resumes in order to present to the user, the terms which contributed to the model decision. Keywords Skill-gap Resume Skills extraction Multi-label classification Convolutional neural network Model explanation
1 Introduction The Association for Talent Development (ATD) defines a skill-gap as a significant gap between an organization’s current capabilities and the skills it needs to achieve its goals and meet customer demand [7]. Organizations bridge the skills gap by hiring candidates with specific skills to perform critical tasks. Nowadays, hiring processes are often conducted through the Internet. Applications (resumes and cover letters) are sent via e-mails, web sites or job posting platforms (indeed.com, freelancer.com, upwork.com, ...). The number of applications for a particular job can be very important, making the candidates selection cumbersome. It is to solve this problem that job& Kameni Florentin Flambeau Jiechieu [email protected] Norbert Tsopze [email protected] 1
Department of Computer Science, University of Yaounde I, Yaounde, Cameroon
2
IRD, UMMISCO, F-93143 Bondy, France
resume matching algorithms have been developed in recent years in order to quickly find candidates whose skills match those required to perform the job. But, many of these algorithms require user inputs [13, 16, 27]: a user should input his skills as keywords list; as well, skills needed to perform the job are supposed to be known in advance. The matching then consists in computing a similarity score between competences of candidates with those required and ranking the candidates according to their sc
Data Loading...
