1. Gather words as many as you can at least over 100M words from the internet.
2. Find some basic statistics of the corpus and display them visually like charts.
3. Embed the words as vectors by machine learning like word2vec and display them in 2D or 3D
this is not a school assignment. I am a self-taught programmer and taking a Udemy course called Natural Language Processing with Deep Learning in Python. I had built a conference system using Python and Freepbx, and I am looking for ways to add some language features. Here I am, I'd like to see this in action where I can learn at least this can be done.
I've got Django and tensorflow working in my server and have a pythonanywhere hosting service, and completed a 70-hour Machine-learning class from a vocational school.
You will have to set up one to work out your solution in my settings (a new Digital Ocean server), so that I can revisit as much as I need. Some documentation is also necessary.
Project budget: 200USD
9 фрилансеров(-а) в среднем готовы выполнить эту работу за $154
Hello. I have read your project details before placing my bid. I can assure you that I can deliver high quality work on time. I am willing to start immediately. Thank you very much.
Over three years of working with this kind of projects from statistics and data analysis, working with big numbers of datasets including analysis and planning
I am actively researching in the field of NLP from last few years, we can have a conversation. Connect to my LinkedIn for further conversations :)