An Exploration of Representation Learning and Sequential Modeling Approaches for Supervised Topic Classification in Job Advertisements

Loading...
Thumbnail Image

URL

Journal Title

Journal ISSN

Volume Title

Perustieteiden korkeakoulu | Master's thesis

Date

2016-10-27

Department

Major/Subject

Machine Learning and Data Mining

Mcode

SCI3015

Degree programme

Master’s Programme in Machine Learning and Data Mining (Macadamia)

Language

en

Pages

94+9

Series

Abstract

This thesis applies the explorative double diamond design process borrowed to iteratively frame a research problem applicable in the context of a recruitment web service and then find the best approach to solve it. Thereby the problem focus is laid on multi-class classification, in particular the task of labelling sentences in job advertisements with one of six topics which were found to be covered in every typical job description. A dataset is obtained for evaluation and conventional N-Gram Vector Space models are compared with Representation Learning approaches, notably continuous distributed representations, and Sequential Modeling techniques using Recurrent Neural Networks. Results of the experiments show that the Representation Learning and Sequential Modeling approaches perform on par or better than traditional feature engineering methods and show a promising direction in and beyond research in Computational Linguistics and Natural Language Processing.

Description

Supervisor

Gionis, Aristides

Thesis advisor

Mathioudakis, Michael

Keywords

natural language processing, computational linguistics, representation learning, sequential text modeling, text classification, job advertisements

Other note

Citation