Job Tailored Resume Content Generation
Sumedh S. Kale, William Andreopoulos · 2023
Generally candidates apply to multiple jobs with a single resume and do not tend to customize their resume to match the job description. This hampers their chances of getting a resume shortlisted for the job. The project aims to help such candidates build job tailored resumes that help them create a customized and targeted resume for a specific job. The tool specifically targets candidates’ employment work history for resume content generation. We create a synthetic dataset built from candidates’ employment history and online job descriptions. We use natural language processing (NLP) techniques to extract and organize the dataset, experiment with multiple dataset variations and cite ways to effectively build the dataset for the proposed task. We then use natural language generation by fine tuning GPT-2 for the task of resume content generation. Finally we evaluate the fine tuned model on various metrics and report our findings.