@inproceedings{bhola-etal-2020-retrieving,
title = "Retrieving Skills from Job Descriptions: A Language Model Based Extreme Multi-label Classification Framework",
author = "Bhola, Akshay and
Halder, Kishaloy and
Prasad, Animesh and
Kan, Min-Yen",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.513",
doi = "10.18653/v1/2020.coling-main.513",
pages = "5832--5842",
abstract = "We introduce a deep learning model to learn the set of enumerated job skills associated with a job description. In our analysis of a large-scale government job portal mycareersfuture.sg, we observe that as much as 65{\%} of job descriptions miss describing a significant number of relevant skills. Our model addresses this task from the perspective of an extreme multi-label classification (XMLC) problem, where descriptions are the evidence for the binary relevance of thousands of individual skills. Building upon the current state-of-the-art language modeling approaches such as BERT, we show our XMLC method improves on an existing baseline solution by over 9{\%} and 7{\%} absolute improvements in terms of recall and normalized discounted cumulative gain. We further show that our approach effectively addresses the missing skills problem, and helps in recovering relevant skills that were missed out in the job postings by taking into account the structured semantic representation of skills and their co-occurrences through a Correlation Aware Bootstrapping process. We further show that our approach, to ensure the BERT-XMLC model accounts for structured semantic representation of skills and their co-occurrences through a Correlation Aware Bootstrapping process, effectively addresses the missing skills problem, and helps in recovering relevant skills that were missed out in the job postings. To facilitate future research and replication of our work, we have made the dataset and the implementation of our model publicly available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bhola-etal-2020-retrieving">
<titleInfo>
<title>Retrieving Skills from Job Descriptions: A Language Model Based Extreme Multi-label Classification Framework</title>
</titleInfo>
<name type="personal">
<namePart type="given">Akshay</namePart>
<namePart type="family">Bhola</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kishaloy</namePart>
<namePart type="family">Halder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Animesh</namePart>
<namePart type="family">Prasad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce a deep learning model to learn the set of enumerated job skills associated with a job description. In our analysis of a large-scale government job portal mycareersfuture.sg, we observe that as much as 65% of job descriptions miss describing a significant number of relevant skills. Our model addresses this task from the perspective of an extreme multi-label classification (XMLC) problem, where descriptions are the evidence for the binary relevance of thousands of individual skills. Building upon the current state-of-the-art language modeling approaches such as BERT, we show our XMLC method improves on an existing baseline solution by over 9% and 7% absolute improvements in terms of recall and normalized discounted cumulative gain. We further show that our approach effectively addresses the missing skills problem, and helps in recovering relevant skills that were missed out in the job postings by taking into account the structured semantic representation of skills and their co-occurrences through a Correlation Aware Bootstrapping process. We further show that our approach, to ensure the BERT-XMLC model accounts for structured semantic representation of skills and their co-occurrences through a Correlation Aware Bootstrapping process, effectively addresses the missing skills problem, and helps in recovering relevant skills that were missed out in the job postings. To facilitate future research and replication of our work, we have made the dataset and the implementation of our model publicly available.</abstract>
<identifier type="citekey">bhola-etal-2020-retrieving</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.513</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.513</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>5832</start>
<end>5842</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Retrieving Skills from Job Descriptions: A Language Model Based Extreme Multi-label Classification Framework
%A Bhola, Akshay
%A Halder, Kishaloy
%A Prasad, Animesh
%A Kan, Min-Yen
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F bhola-etal-2020-retrieving
%X We introduce a deep learning model to learn the set of enumerated job skills associated with a job description. In our analysis of a large-scale government job portal mycareersfuture.sg, we observe that as much as 65% of job descriptions miss describing a significant number of relevant skills. Our model addresses this task from the perspective of an extreme multi-label classification (XMLC) problem, where descriptions are the evidence for the binary relevance of thousands of individual skills. Building upon the current state-of-the-art language modeling approaches such as BERT, we show our XMLC method improves on an existing baseline solution by over 9% and 7% absolute improvements in terms of recall and normalized discounted cumulative gain. We further show that our approach effectively addresses the missing skills problem, and helps in recovering relevant skills that were missed out in the job postings by taking into account the structured semantic representation of skills and their co-occurrences through a Correlation Aware Bootstrapping process. We further show that our approach, to ensure the BERT-XMLC model accounts for structured semantic representation of skills and their co-occurrences through a Correlation Aware Bootstrapping process, effectively addresses the missing skills problem, and helps in recovering relevant skills that were missed out in the job postings. To facilitate future research and replication of our work, we have made the dataset and the implementation of our model publicly available.
%R 10.18653/v1/2020.coling-main.513
%U https://aclanthology.org/2020.coling-main.513
%U https://doi.org/10.18653/v1/2020.coling-main.513
%P 5832-5842
Markdown (Informal)
[Retrieving Skills from Job Descriptions: A Language Model Based Extreme Multi-label Classification Framework](https://aclanthology.org/2020.coling-main.513) (Bhola et al., COLING 2020)
ACL