Abstract: Extracting knowledge from text data has always been one of the most researched topics in machine learning, but only recently we witnessed breakthroughs that put NLP in the spotlight. Many pieces of information are stored in unstructured data, like text, which is extremely important in many different fields, from finance to social media and e-commerce.
In this course we will go through Natural Language Processing fundamentals, such as pre-processing techniques,tf-idf, embeddings, and more. It will be followed by practical coding examples, in python, to teach how to apply the theory to real use cases.
The goal of this workshop is to provide the attendees all the basic tools and knowledge they need to solve real problems and understand the most recent and advanced NLP topics.
Lesson 1 Text Representation
Theory: Familiarize yourself with NLP fundamentals and text preprocessing, to prepare the data for our models. We will go through the main steps like removing stopwords, stemming, One-Hot Encoding, and more.
Exercise: Apply text preprocessing methods on a simple dataset.
Outcome: You will be able to apply to the appropriate methodology to preprocess the text.
Lesson 2 Topic Modeling (45m)
Theory: We will see what LDA is and how it can help to extract information from documents. We will also try different clustering techniques and implement a Non-negative Matrix factorization.
Exercise: Apply topic modeling techniques on a simple text.
Outcome: You will be able to apply to extract the main information from documents using topic modeling techniques.
Lesson 3 Text Classification (30m)
Theory: We will learn how it’s possible to represent text and how a classifier can use this representation. We will use TF-Idf and experiment with a couple of supervised learning models.
Exercise: Build an NLP pipeline to perform classification.
Outcome: You will be able to solve a text classification problem end to end.
Lesson 4 Introduction to Deep Learning in NLP (45m)
Theory: Understand word embedding, how it works, and how to use it. We will go through the main concepts behind word embedding and see some practical examples using the Gensim library.
Exercise: Leveraging python deep learning libraries to create an NLP pipeline for sentiment analysis.
Outcome: You will be able to use word embedding to perform any text classification task.
Lesson 5 Overview of Advanced Deep NLP
We will introduce the most recent development of Deep learning in NLP, in particular we will see how to leverage BERT architectures and their pre-trained models to solve NLP problems such as summarization, generation and classification.
We will be using python in all exercises therefore some python knowledge is required. Some machine learning knowledge is beneficial but not required. We will introduce all the basic concepts needed but without spending much time on the most basic ML concepts.
Bio: Laura Skylaki is a Manager of Applied Research in Thomson Reuters Labs, where she leads advanced machine learning projects in the domain of Legal and Tax AI.With a career spanning more than a decade at the intersection of research and practical application, she has contributed technical expertise in diverse fields such as bioinformatics and stem cell biology, image processing and natural language processing. She holds a doctorate in stem cell bioinformatics from the University of Edinburgh, UK, and has been publishing on machine learning applications in leading academic journals since 2012.
Laura Skylaki, PhD
Manager of Applied Research | Thomson Reuters Labs