NOTE: While this is a virtual class, we will cap it at classroom size so that there is a strong focus on learning. There is a nominal charge for the 6 hours of lecture - please sign up early as we will keep the attendee count low. This is NOT a MOOC. Registration also includes a 1-year SFBay ACM membership ($20 value)
Abstract - Natural Language Processing (NLP) is the fastest-growing field of deep learning with interest and funding from top AI companies to solve problems of language, text, and unstructured information. This has resulted in a tremendous focus on model building that combines language, mathematics, and computer science.
This workshop will focus on problems of text summarization, question answering, and sentiment classification using modern approaches to model-building (GNMT, BERT). We will apply this to real-world problems to create an NLP pipeline on top of the PyTorch framework and spaCy.
Content: You will have access to all the notebooks, training material to build your own apps. You should be able to directly work on these using Google Colab. For the Workshop itself, we will have AWS instances available for use.
Key topics covered
This will be a very lecture and lab heavy workshop. We will plan on a 1-hour webinar before the workshop weekend to get you ready for the class so that you can get the most out of it and come away with a tangible outcome. We will have several TAs on-site to help with the learning process, but expect the class to move at a fairly fast clip!)
Day 1: June 27, 10am-1pm, Pacific Time
- Natural Language Process & Transfer Learning
- Fundamentals and application of Language Modeling Tools
- Use NLP pipeline to process documents, Word Vectors
- Introduction to SpaCy and PyTorch
Lab: Multiple labs using NLP pipeline
Day 2: June 28, 10am-1pm Pacific Time
- Introduction to pre-trained models such as BERT
- Sentiment analysis
- Text summarization
Lab on "Question Answering" as a practical implementation of the learning.
Note on Labs:
More than 60% of the time will be spent on labs. The labs will use Jupyter/Python. Familiarity with Python and Deep Learning will be very useful. Attendees should have chrome installed.
⇒ REGISTRATION
Organizer & SFBay ACM Prof Dev Chair: Yashesh Shroff @yashroff
For more information about Registration, please contact SF Bay Chapter of the ACM, yshroff -AT- g | m | a i l
We look forward to seeing you at the workshop!
|