CV Retrieval System based on job description matching using hybrid word embeddings

Fernández-Reyes, Francis C.; Shinde, Suraj

doi:10.1016/j.csl.2019.01.003

Cited by 8 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent advancements in NLP offer opportunities to improve these methods: Particularly word embeddings-i.e., vector representations of words in a semantic vector spaceare able to deal with similar words and synonyms since in this representation word embeddings of words with similar context are nearby in vector space. [8] use word embeddings from Word2Vec [13] to match CVs to jobs. [11] combine a knowledge graph and BERT for finding suitable candidates in a corpus of CVs.…”

Section: Related Workmentioning

confidence: 99%

“…For a certain job position, (1) Skill Scanner takes a CV, a job posting or a learning curriculum as input, (2) extracts the skills of the provided document, (3) compares the document's extracted skills to a skill set which represents the job market's needs (market skills), and (4) returns information of which market skills are covered or missing in the provided document compared to the job market's needs [8].…”

Section: A Pipeline To Extract Vectorize Cluster and Compare Skillsmentioning

confidence: 99%

“…To compute distances between skills we mapped the skills to a semantic vector space. Like [8,11], we experimented with word embeddings to vectorize the skills. To represent the skills which usually consist of several words, we investigated stacking and averaging the word embeddings in a skill after they were produced with Word2Vec [13] and GloVe [22].…”

Section: Vectorizing Skillsmentioning

confidence: 99%

“…However, this way employers, job seekers and educational institutions usually use AI in isolation from one another. For example, [8] present a Word2Vec-based [9] recommendation system that informs employers how well job seekers' CVs fit job postings. LinkedIn has a system that recommends jobs to job seekers based on their CVs [10].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Skill Scanner

Schlippe

Bothmer

2023

Int. J. Adv. Corp. Learn.

View full text Add to dashboard Cite

Skills are the common ground between employers, job seekers and educational institutions which can be analyzed with the help of artificial intelligence (AI), specifically natural language processing (NLP) techniques. In this paper we explore a state-of-the-art pipeline that extracts, vectorizes, clusters, and compares skills to provide recommendations for all three players—thereby bridging the gap between employers, job seekers and educational institutions. As companies hiring data scientists report that it is increasingly difficult to find a so-called "unicorn data scientist" [1], we conduct our experiments and analysis using companies’ job postings for a data scientist position, job seekers’ CVs for that position, and a curriculum from a master's program in data science. However, our investigated methods and our final recommendation system can be applied to other job positions as well. Our best system combines Sentence-BERT [2], UMAP [3], DBSCAN [4], and K-means clustering [5]. To also evaluate feedback from potential users, we conducted a survey, in which the majority of employers’, job seekers’ and educational institutions’ representatives state that with the help of our automatic recommendations, processes related to skills are more effective, faster, fairer, more explainable, more autonomous and more supported.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: A Pipeline To Extract Vectorize Cluster and Compare Skillsmentioning

confidence: 99%