Abstract: Being specialized in domains like computer vision and natural language processing is no longer a luxury but a necessity which is expected of any data scientist in today’s fast-paced world! With a hands-on and interactive approach, we will understand essential concepts in NLP along with extensive hands-on examples to master state-of-the-art tools, techniques and methodologies for actually applying NLP to solve real-world problems. We will specifically be focusing on deep learning and deep transfer learning models to learn and solve popular tasks using NLP including NER, Classification, Search / Information Retrieval, Summarization, Classification, Language Translation, Q&A systems.
Module 1: NLP Applications with Traditional Deep Learning
We will look at several popular applications of NLP in this module and go through hands-on examples. This includes word embeddings, text classification and sentiment analysis, sequential deep learning models, language translation
Key Focus Areas: Embeddings, Similarity \ Information Retrieval, Language Translation (seq2seq \ attention), Classification & Sentiment Analysis (deep learning models)
Module 2: NLP Applications with Deep Transfer Learning
We will dive into some of the latest and best advancements which have happened in the last few years in the world of NLP, thanks to deep transfer learning. We will cover a deep conceptual understanding of the transformer architecture and look at some hands-on examples of text classification and multi-task NLP using transformers where we look at solving NER, Q&A, sentiment analysis, summarization, translation using effective constructs like the transformers pipeline and even teach you how you can fine-tune some of these models on custom data.
Key Focus Areas: Search with Contextual Transformer Embeddings vs. Word Embeddings, Text Classification (with pre-trained embeddings, universal sentence encoders and transformers), Multi-task NLP with transformer pipelines (sentiment analysis, NER, text generation, summarization, question-answering, translation). Fine-tuning\training transformers (tips \ guidelines) with examples e.g NER and Language Translation
Knowledge of Python is essential. Having basic knowledge of classical NLP and Machine Learning is useful.
Bio: Dipanjan (DJ) Sarkar is a data science consultant and published author, and was recognized as a Google Developer Expert in Machine Learning by Google in 2019. He currently works as a lead data science consultant at Schaffhausen Institute of Technology Academy, Zurich. Dipanjan has led advanced analytics initiatives working with Fortune 500 companies like Intel, Applied Materials, Red Hat / IBM. He works on leveraging data science, machine learning and deep learning to build large- scale intelligent systems. Dipanjan also works as an independent consultant, mentor and AI advisor in his spare time collaborating with multiple universities, organizations and startups across the globe.
His passion includes solving challenging data problems as well as educating and helping people upskill in all things data. Dipanjan has also been recognized as one of the top ten Data Scientists in India in 2020, 40 under 40 Data Scientists, 2021 and Top 50 AI Thought Leaders by Global AI Hub, Switzerland. In his spare time he loves reading, gaming, watching interesting documentaries, football. He is also a strong supporter of open-source and publishes his code and analyses from his books, articles and experience on GitHub at https://github.com/dipanjanS and LinkedIn at https://www.linkedin.com/in/dipanzan
Dipanjan (DJ) Sarkar
Lead Data Scientist / Google Developer Expert - ML | SIT Academy, Zurich