GPT-Cover Letters
It is a resume to cover letter generator which uses chatgpt as test generater and custom nlp model to extract resume features.
Created on 2nd April 2023
•
GPT-Cover Letters
It is a resume to cover letter generator which uses chatgpt as test generater and custom nlp model to extract resume features.
The problem GPT-Cover Letters solves
Writing a tailored cover letter that effectively communicates a candidate's
qualifications and experience while also aligning with a specific job description can
be a significant challenge for job seekers. This challenge often results in missed job
opportunities and added stress during the job application process.
• Motivation - Writing a cover letter can be a daunting task for job seekers, especially
when they have to tailor their application to different job descriptions. Many
candidates struggle to convey their qualifications and experience in a compelling
manner, which could lead to missed opportunities. To address this challenge, we
introduce a web app that generates a cover letter specific to the job description by
taking the candidate's resume as input.
Challenges we ran into
Feasibility Study
Our app is built using state-of-the-art technologies and hosted on the cloud, making
it highly scalable and accessible from anywhere in the world. It is also designed to be
user-friendly, with a simple and intuitive interface that requires no technical
knowledge to use.
Approach
We will use OpenAI’s GPT-3.5-Turbo API for the current prototype of the app with :
• Sentiment Analysis - This can help the model to generate a cover letter that
matches the tone of the job posting and expresses the candidate's enthusiasm for
the position.
• Part-of-speech (POS) tagging - This technique can be used to analyze the structure
of the job description and the candidate's resume, which can help the model to
identify relevant keywords and phrases to include in the cover letter.
• Text classification - This technique can be used to classify the job description and
the candidate's resume into specific categories to fine-tune the model.