Paper Key : IRJ************256
Author: Dr. S. A. Bhavsar,Rajeshwari Shinde,Vaishnavi Kharche,Akanksha Ghotekar
Date Published: 07 Nov 2024
Abstract
Automated resume parsing is a crucial component in modern recruitment processes, enabling the efficient extraction of relevant candidate information from resumes. Traditional methods often rely on keyword matching, which can be imprecise and overlook contextual relevance. This paper explores the application of Named Entity Recognition (NER) for automated resume parsing, offering a more accurate and context-aware approach. NER, a subset of natural language processing (NLP), involves identifying and classifying entities in text into predefined categories such as names, locations, dates, and job titles. In the context of resume parsing, NER models can be trained to recognize and extract key information such as candidate names, contact details, educational qualifications, work experience, and skills. This approach not only improves the accuracy of data extraction but also reduces the need for manual intervention, thereby speeding up the recruitment process. The proposed NER-based resume parser leverages machine learning algorithms, particularly those designed for sequence labeling tasks, to automatically identify and categorize relevant information from various resume formats. By doing so, it addresses common challenges such as the variability in resume structures and the presence of unstructured text. The implementation of this system can significantly enhance the efficiency of recruitment pipelines, enabling organizations to quickly shortlist candidates based on precise criteria. This paper discusses the development, training, and evaluation of the NER model, demonstrating its potential to revolutionize resume parsing in the hiring process.