Created with AI (Bing Image Creator)Abstract
Natural Language Processing (NLP) is a thriving and ever-expanding field of study. We will cover the fundamentals of NLP in this session, including text processing, text representation, text classification, embeddings, and more. We’ll also look at some of the most popular NLP libraries, including NLTK, Gensim, SpaCy, and HuggingFace. In addition, we will get our hands dirty by developing several real-world NLP tasks. The purpose of this session is to provide you with a solid foundation of the NLP area before delving deeper into sequential deep learning models like RNNs, LSTMs, and Transformers.
Date
Nov 2, 2023 10:00 AM — 3:30 PM
Location
Online
Sources and Useful Links
🎞️ Videos
- “Robert Meyer - Analysing user comments with Doc2Vec and Machine Learning classification” by Robert Meyer
- “A Hackers’ Guide to Language Models” by Jeremy Howard
- “Byte Pair Encoding Tokenization” by HuggingFace
- “1 5 Byte Pair Encoding” by Professor Dan Jurafsky
📚 Blog posts
📄 Notebooks
- “01 - Trained Word Embeddings with Gensim.ipynb” by Jay Alammar
- “02 - Embedding Songs to Make Recommendations.ipynb” by Jay Alammar
- “NLP-MasterTemplate.ipynb” by Hariom Tatsat
📖 Books
- “Introduction to Information Retrieval”, by Christopher D. Manning, Prabhakar Raghavan and Hinrich Schütze
Parsa Abbasi
MSc Student
He is an AI graduate student with a keen interest in graph neural networks, relational graphs, natural language processing, and deep learning.