Information extraction from Resumes/CVs written in English
Model Description
This model is designed for information extraction from resumes/CVs written in English. It employs a transformer-based architecture with spaCy for named entity recognition (NER) tasks. The model aims to parse various sections of resumes, including personal details, education history, professional experience, skills, and certifications, enabling users to extract structured information for further processing or analysis.
Model Details
Feature | Description |
---|---|
Language |
English |
Task |
Named Entity Recognition (NER) |
Objective |
Information extraction from resumes/CVs |
Spacy Components |
Transformer, Named Entity Recognition (NER) |
Author |
Youssef Chafiqui |
NER Entities
The model recognizes various entities corresponding to different sections of a resume. Below are the entities used by the model:
Label | Description |
---|---|
'FNAME' | First name |
'LNAME' | Last name |
'ADDRESS' | Address |
'CERTIFICATION' | Certification |
'EDUCATION' | Education section |
'EMAIL' | Email address |
'EXPERIENCE' | Experience section |
'HOBBY' | Hobby |
'HSKILL' | Hard skill |
'LANGUAGE' | Language |
'PHONE' | Phone number |
'PROFILE' | Profile |
'PROJECT' | Project section |
'SSKILL' | Soft skill |
Evaluation Metrics
Type | Score |
---|---|
F1 score |
81.98 |
Precision |
83.33 |
Recall |
80.68 |
Usage
Presequities
Install spaCy library
pip install spacy
Install Transformers library
pip install transformers
Download the model
pip install https://huggingface.co/ychafiqui/en_cv_info_extr/resolve/main/en_cv_info_extr-any-py3-none-any.whl
Load the model
import spacy
nlp = spacy.load("en_cv_info_extr")
Inference using the model
doc = nlp('put your resume here')
for ent in doc.ents:
print(ent.text, "-", ent.label_)
- Downloads last month
- 44
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Space using ychafiqui/en_cv_info_extr 1
Evaluation results
- NER Precisionself-reported0.833
- NER Recallself-reported0.807
- NER F Scoreself-reported0.820