The model I’m going to introduce today is a NLP model that generates a resume by entering a few words.
If you would like to check the project right away, please click on the following link.
A résumé : Document created by a person in order to present their background, skills, and accomplishments.
If you are preparing for a job interview, writing a resume is inevitable. Human resources managers will check the resumes of numerous applicants, so be sure to clearly describe your skills and all the relevant achievements you have accomplished so far in your resume. Perhaps you have struggled when trying to elaborate a resume as it’s easy to get stuck in what or how to properly write a resume.
For this project, the resume data I used in order to train the model was available from Kaggle. The data includes information that can be found in resumes from various fields such as Java Developer and DevOps Engineer.
Let’s take a look at the first resume below
Data Science Assurance Associate
Data Science Assurance Associate - Ernst & Young LLP
jQuery- Experience - 24 months
Python- Experience - 24 monthsCompany Details
MULTIPLE DATA SCIENCE AND ANALYTIC PROJECTS (USA CLIENTS)
TEXT ANALYTICS - MOTOR VEHICLE CUSTOMER REVIEW DATA * Received customer feedback survey data for past one year. Performed sentiment (Positive, Negative & Neutral) and time series analysis on customer comments across all 4 categories.
Created heat map of terms by survey category based on frequency of words * Extracted Positive and Negative words across all the Survey categories and plotted Word cloud.
Created customized tableau dashboards for effective reporting and visualizations.
CHATBOT * Developed a user friendly chatbot for one of our Products which handle simple questions about hours of operation, reservation options and so on.
This chat bot serves entire product related questions. Giving overview of tool via QA platform and also give recommendation responses so that user question to build chain of relevant answer.
*This too has intelligence to build the pipeline of questions as per user requirement and asks the relevant /recommended questions.
창짖 FAP is a Fraud Analytics and investigative platform with inbuilt case manager and suite of Analytics for various ERP systems.
*It can be used by clients to interrogate their Accounting systems for identifying the anomalies which can be indicators of fraud by running advanced analytics
When analyzing the data, it seems that we need to remove the asterisk (*) denoting the item and then delete the word that caused the encoding error. In addition, the data includes information not only from a developer’s resume, but also a HR’s (Human Resource) resume, a Mechanical Engineer’s resume, etc., so it is necessary to filter it.
- Using Demo
First, let’s create a resume through a Demo format provided by Ainize.
After entering the base text, press the button “execute” in order to check the resume creation result. The demo can be found at the link .
- Using the API
This time let’s write a resume using the API provided by Ainize. You can check the information on the API in the link .
You can create a resume by entering text_input and setting the content length. However, please note that if you set the content length too large, an error will occur (it seems like a suitable content length of 10 to 30 will work fine ).
- Train the model yourself
Now, we will use the model by training it through Teachable NLP.
Teachable NLP is a program that helps you fine-tuning NLP models without complex code or GPU. Anyone can upload the data to be used for training and only by doing this, the model will be automatically trained and distributed in the form of an API. The trained model can be used through this API.
After the pre-processed data was put in Teachable-NLP, the model size was set to “small” and the epoch was set to “3” and after this, the GPT-2 model was fine-tuned. When the training process is over, click “Test your model” and click to open the TabTab screen where you can create your own resume.
Writing a resume doesn’t seem to be an easy task. I also had a hard time not knowing what to write when writing my resume in the beggining. I think it would have been easier to write a resume if I knew this model beforehand.
Lets say that if such a model would have been provided by an employment support service, it would be easy to obtain a resume to be used for model learning (under the premise that the personal information problem would have been solved in advance) perhaps there would be more people looking for this type of service. Thanks for reading!