RESUME SUMMARIZER AND JOB DESCRIPTION MATCHER USING NATURAL LANGUAGE PROCESSING AND SPACY

Abstract

In the HR recruitment process, one pivotal stage is "Summarizing & Screening." At this juncture, recruiters grapple with the laborious task of manually sifting through a myriad of resumes to shortlist suitable candidates. This project aims to streamline and automate this process using two innovative tools. Firstly, the "Resume Summarizer" leverages advanced natural language processing techniques to swiftly extract pertinent details from candidates' resumes, offering a concise summary that underscores their skills, experience, and qualifications. This summary can be tailored to match specific job requirements, facilitating recruiters in the comparative evaluation of multiple candidates. Secondly, the "Job Description Matcher" assists recruiters in expeditiously and accurately aligning job descriptions with candidate resumes. By employing natural language processing, this tool identifies keywords and phrases that align with the job opening's prerequisites, generating a compatibility score to rank resumes according to their alignment with the job description. This innovation greatly expedites candidate selection and enhances recruiters' efficiency. Importantly, this project employs a unique approach, incorporating regular expressions to extract essential information from resumes, setting it apart from existing NLP-based models and systems. Keywords: Natural Language Processing, Text Analysis, Data Extraction, Keyword matching, Regular Expressions, Optical Character Recognition (OCR), N-Gram Model, Name Entity Recognition (NER), Unsupervised NER.