WSP 367 — Deep Learning for Natural Language Processing (ICME Workshop)
Big data has changed the way we work, live, and play. Data science—developing and testing models and algorithms—helps us gain knowledge for ourselves and provide insights to others.
Deep Learning for Natural Language Processing is one of ten workshops included in Fundamentals of Data Science, a series of one-day workshops offered by the Stanford Institute for Computational and Mathematical Engineering (ICME). Fundamentals of Data Science provides an introduction to multiple aspects of data science for those who are new to the field and those seeking to broaden their education and skills in data science. Students can sign up for one workshop, or several throughout the week. Students who complete four workshops will qualify for the Stanford ICME Fundamentals of Data Science Summer Workshops Certificate of Completion.
These workshops are not eligible for tuition discounts through Stanford Continuing Studies, but ICME offers discounts for eligible affiliates and partners. See below for details:
Stanford staff and full-time Stanford students: You may be eligible for a tuition discount if you register directly through ICME. The tuition for Stanford staff is $100 and the tuition for full-time Stanford students is $75. For more information and to register with these discounts, visit https://sto.stanfordtickets.org/icme2020/homepage.
ICME partners and affiliates qualify for a discount. If you think you qualify and have not received a discount code separately, email firstname.lastname@example.org. You will need to register through ICME's website.
Workshop: Deep Learning for Natural Language Processing
Instructor: Luke de Oliveira, Technical Lead, Language Understanding, Twilio
This workshop will focus on practical applications and considerations of applying deep learning to Natural language processing (NLP). We will start by drawing inspiration from more traditional NLP approaches, and show how many modern deep learning-based algorithms have deep roots in traditional techniques, while showing how deep learning has enabled new improvements. This workshop will heavily focus on student's understanding of problem templates in applied natural language processing, and about identifying application patterns. We will have a practical focus, targeting algorithms, and problem templates which are able to be deployed and used today. We will cover the different components that go into deep learning systems, including word vector representations (word2vec, GloVe), contextual representations (ELMo, BERT), and general model components such as convolutional layers, Transformers, and others. We will also cover introductory material in applications such as classification, intent understanding, and others. We will be using the Keras library for a practical session where we will implement select models.
Some experience with both Python and Machine Learning is required. It is recommended that students take the Machine Learning and Deep Learning ICME workshops for a better understanding of the material included in this NLP workshop.
Please note: Although the enrollment limit for this workshop is set to 60 Continuing Studies students, this course is designed for the entire Stanford community, and enrolled Continuing Studies students will be joined in the classroom by Stanford graduates and undergraduates. Students should expect a large class.