Explore Prompting Methods in Natural Language Processing

Today we talk about prompting methods with language models and some applications they have with weak supervision. We’re essentially going to be using this paper as a template. This paper is a great survey over some methods in prompting from the last few years from some folks over at Carnegie Mellon, and it’s called “Pre-Train Prompt and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing.” On top of the paper, they also have a great resource as a nice digestible web page that you can go to at Pretrain NLPedia, which I highly recommend. It’s got a bunch of the information just distilled really well with a lot of helpful figures and sectioning for some of the more complex topics. But yeah, let’s dive right in. ML Whiteboard is an informal session where data scientists, machine learning engineers, and developers along with Snorkel AI team members join to discuss the latest research and new techniques for machine learning, deep learning, NLP, and more. More related videos: https://www.youtube.com/playlist?list=PLZePYakcDhmhWPWYZpNgk8D4XzyFgDDqc More related videos: https://www.youtube.com/playlist?list=PLZePYakcDhmgkVt_r_QZwv9MeUzazZWGv More related videos: https://www.youtube.com/playlist?list=PLZePYakcDhmgz_Mcr2D0nS1vqhuSplq6s #languagemodels #machinelearning #datascience