Hello, thank you for your thoughtful lecture. I like it when we first explain principles, concepts and limitations before diving into technical details and solutions. Most people only focus on showing of how they did it.
@@AIwithSohini Is there a way I can get in touch? I am trying to create a scholarshipp predictor but having some challenges. The goal is for the user to enter his/her field of interest or the model scan a CV and predict the likely scholarship the user can apply to
Hello sohini can I get a tutorial which is step by step on building a resuming screening using machine learning and NLP to quickly and accurately filter and rank resume based on job descriptions
Hello there thanks for the question. What you are looking for is called intelligent character recognition. Here is my video on using V7 for such tasks. ru-vid.com/video/%D0%B2%D0%B8%D0%B4%D0%B5%D0%BE-6QUc1tNUlBo.htmlsi=OOeAR6ck9-7iX5Eh. Also ChatGPT can do this task very well as well. My latest video should explain that. Thanks and stay tuned
Helloo ma'am, just wanted to ask the dataset you imported from kaggle was already sorted and has categorized data. but if i have 100 resume in PDF formate how can i extract data in such a way that it goes perfectly to the exact column in cvs or excel, knowing that resume do have different formates and creating a csv manually like filling all columns by hand isnt an option. kindly explain me thankyou.
Thanks for the great question! If your resumes exist in pdf format the first step is to extract the text from pdf (so OCR models, or using pdf2text modules in python pypi.org/project/pdftotext/ Pytesseract is another such module that will extract the text from pdf. Once you have the text, then you can proceed with the method in the video. Hope this helps. Thanks and stay tuned!
Thanks for the videos and detailed explanation/excited to learn from you, Mam. Currently, I am also doing nlp related tasks like Text classification/creating Question answering system and it is highly interesting domain. I believe the forthcoming videos will be on nlp tasks. Can you also add some discussions or tips on Huggingface/spacy libraries/fine tuning?
Hello Venkatesan, Yes, my future videos will be using hugging face models. I found the colab notebooks for BERT to be most useful. Here is the link huggingface.co/docs/transformers/notebooks
In my experience lot of job descriptions are not particularly well formed and their use of language is also non standard. That makes using NLP a challenge. I first focus on extraction of facts such as skills with simple keywords matching. Might use lemmatization to handle plurals. Have to look for ways to handle spelling errors. Data is dirty.
That’s great steps. I will make sure to highlight them in a coffee session. Another difficult area is gauging experience for each skill. That can be a real hurdle for skill level match finding.
Hello there. Years of experience is often a tricky thing to estimate. The easiest method is to look for the skills and check to see if the resume states beginner intermediate or expert levels. Beginner would be less than 1 year, intermediate is 1-2 yrs and expert is more than 2 years of experience. Once you have that look through the experiences in past to find number of occurrences in experiences to support this estimation. Hope this helps. Thanks and stay tuned
Hello there and thanks for your question. Your first step starting from a pdf document would be to run an ocr system to convert all the contents into text. There are several pdf to text converters online available for free. So use any one and generate the txt data and then follow the steps in the video. Thanks and stay tuned.
Hello there. You will need to read each resume one by one. Then the text in each section like skills, experience get added to a separate column. So it is a pandas data frame operation. Hope that helps.
