Resume Parser using hybrid approach to enhance the efficiency of
Automated Recruitment Processes
- Nirmiti Bhoir,
- Mrunmayee Jakate,
- Snehal Lavangare,
- Aarushi Das,
- Sujata Kolhe
Abstract
This study provides a novel resume parsing solution using a hybrid Spacy
Transformer BERT and Spacy NLP methodology. The main goal is to create a
resume parser that can efficiently extract pertinent data from
unstructured resumes that do not adhere to a predetermined resume
structure and may contain information presented in a non-standardized
manner. We also intend to investigate the usage of video resumes as a
fresh source of candidate data and put forth a cutting-edge method for
video resume parsing that combines visual and audio processing methods.
We employed a hybrid methodology of Spacy Transformer BERT and Spacy NLP
to accomplish these goals. A pre-trained deep learning model called
Spacy Transformer BERT captures the text's semantic meaning, and Spacy
NLP employs natural language processing to glean pertinent information
from it. Our method combines the strengths of the two models for high
accuracy and efficiency in collecting pertinent information from
resumes. Using a dataset of resumes, we ran experiments to gauge how
well our suggested system performed. The outcomes demonstrate that our
system was highly accurate in retrieving pertinent data, including
candidate names, contact information, qualifications, work experience,
and other pertinent characteristics.