06-28, 11:30–12:20 (Asia/Jerusalem), PyData
Join us to learn how to use large language models to solve NLP tasks. Via live coding, we'll demonstrate how to use Few Shot Learning together with Multi-armed Bandit, to tackle the boolean question answering task.
In the era of massive language models (LMs), solving NLP tasks can be as easy as specifying a product need to your engineering team: all you need to do is specify your need in a language the LM can understand. One of the main paradigms in nowadays massive LMs is called Few Shot Learning, where one can specify a set of examples from which the model has to understand the task. This approach can sometimes be as effective as finetuning.
But how do you choose the set of examples to show to the model? Randomly choose them? Try all possible combinations and choose the best one? We propose to formulate this task as a Multi-Armed Bandit problem: There are many possible sets of examples, and we’d like to explore and find the optimal in an efficient way.
In this session we’ll begin with an empty Jupyter Notebook and finish with a complete notebook that tackles the BoolQ task (boolean question answering). This live coding session will be paired with practical advices and insights you can apply to your next NLP task using the Few Shot Learning approach.
Hebrew
Target audience –Data Scientists
Over 13 years of experience as a software engineer and algorithm developer in various domains, including NLP, recommender systems, vision, and cybersecurity.
I am passionate about good quality code, interesting ideas and sophisticated algorithms. I love encountering elegant equations while trying to solve real-life problems.
Seasoned Data Scientist with an emphasis on NLP, classical ML, visualization and experimentation. Driven by great passion for the field, I am inspired by unintuitive insights and inferences made by smart algorithms. In my talks, I try to convey my typical spirit and enthusiasm while delivering crisp takeaways.