Competence-Level Prediction and Resume & Job Description Matching Using Context-Aware Transformer Models

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pages 8456–8466, November 16–20, 2020. c⃝2020 Association for Computational Linguistics 8456 Competence-Level Prediction and Resume & Job Description Matching Using Context-Aware Transformer Models Changmao Li♠, Elaine Fisher♦, Rebecca Thomas♥, Steve Pittard♣, Vicki Hertzberg♦, Jinho D. Choi♠ ♠Department of Computer Science, Emory University, Altanta GA, USA ♦Nell Hodgson Woodruff School of Nursing, Emory University, Altanta GA, USA ♣Department of Biostatistics and Bioinformatics, Emory University, Altanta GA, USA ♥Georgia CTSA Clinical Research Centers, Emory Healthcare, Atlanta GA, USA changmao.li@emory.edu, elaine.fisher@emory.edu, rebecca.s.thomas@emoryhealthcare.org wsp@emory.edu, vhertzb@emory.edu, jinho.choi@emory.edu Abstract This paper presents a comprehensive study on resume classification to reduce the time and la- bor needed to screen an overwhelming number of applications significantly, while improving the selection of suitable candidates. A total of 6,492 resumes are extracted from 24,933 job applications for 252 positions designated into four levels of experience for Clinical Research Coordinators (CRC). Each resume is manually annotated to its most appropriate CRC position by experts through several rounds of triple an- notation to establish guidelines. As a result, a high Kappa score of 61% is achieved for inter- annotator agreement. Given this dataset, novel transformer-based classification models are de- veloped for two tasks: the first task takes a re- sume and classifies it to a CRC level (T1), and the second task takes both a resume and a job description to apply and predicts if the applica- tion is suited to the job (T2). Our best models using section encoding and multi-head atten- tion decoding give results of 73.3% to T1 and 79.2% to T2. Our analysis shows that the pre- diction errors are mostly made among adjacent CRC levels, which are hard for even experts to distinguish, implying the practical value of our models in real HR platforms. 1 Introduction An ongoing challenge for Human Resource (HR) is the process used to screen and match applicants to a target job description with a goal of minimizing recruiting time while maximizing proper matches. The use of generic job descriptions not clearly strat- ified by the level of competence or skill sets often leads many candidates to apply every possible job, resulting in misuse of recruiter and applicant’s time. A more challenging aspect is the evaluation of un- structured data such as resumes and CVs, which represents about 80% of the data processed daily, a task that is typically not an employer’s priority given the manual effort involved (Stewart, 2019). The current practice for screening applications in- volves reviewing individual resumes via traditional approaches, that rely on string/regex matching. The scope of posted job positions varies by the hiring organization type, job level, focus area, and more. The latest advent in Natural Language Processing (NLP) enables the large-scale analysis of resumes (Deng et al., 2018; Myers, 2019). NLP models also allow for a comprehensive analyses on resumes and identification of latent concepts that may easily go unnoticed using a general manual process. This model’s ability to infer core skills and qualifications …

Content truncated to 500 words