We define and advance data and environments to push the AI frontier

Constructing labeling functions (LFs) is at the heart of using weak supervision. We often think of these labeling functions as programmatic expressions of domain expertise or heuristics. Indeed, much of the advantage of weak supervision is that we can save time—writing labeling functions and applying them to data at scale is much more efficient compared to hand-labeling huge numbers of…

Powerful resources to leverage as labeling functions In this post, we’ll use the COVID-FACT dataset to demonstrate how to use existing resources as labeling functions (LFs), to build a fact-checking system. The COVID-FACT dataset contains 4086 claims about the COVID-19 pandemic; it contains claims, evidence for the claims, and contradictory claims refuted by the evidence. The evidence retrieval is formulated…

This post showcases a panel discussion on the academic and industry perspectives of ethical AI, which was moderated by Director of Federal Strategy and Growth, Alexis Zumwalt, Fouts Family Early Career Professor and Lead of Ethical AI (NSF AI Institute AI4OPT), Georgia Institute of Technology, Swati Gupta, Chief Data Officer, Department of the Navy, Thomas Sasalsa, Senior Manager of Responsible…

The founding team of Snorkel AI has spent over half a decade—first at the Stanford AI Lab and now at Snorkel AI—researching programmatic labeling and other techniques for breaking through the biggest bottleneck in AI: the lack of labeled training data. This research has resulted in the Snorkel research project and 150+ peer-reviewed publications. Snorkel’s programmatic labeling technology has been…

The founding team of Snorkel AI has spent over half a decade—first at the Stanford AI Lab and now at Snorkel AI—researching data-centric techniques to overcome the biggest bottleneck in AI: The lack of labeled training data. In this video Snorkel AI co-founder Paroma Varma gives an overview of the key principles of data-centric AI development. What is data-centric AI?…

Showcasing Liger—a combination of foundation model embeddings to improve weak supervision techniques. Machine learning whiteboard (MLW) open-source series In this talk, Mayee Chen, a PhD student in Computer Science at Stanford University focuses on her work combining weak supervision and foundation model embeddings that improve two essential aspects of current weak supervision techniques. Check out the full episode here or…

A primer on active learning presented by Josh McGrath. Machine learning whiteboard (MLW) open-source series This video defines active learning, explores variants and design decisions made within active learning pipelines, and compares it to related methods. It contains references to some seminal papers in machine learning that we find instructive. Check out the full video below or on Youtube. Additionally, a…

Utilizing large language models as zero-shot and few-shot learners with Snorkel for better quality and more flexibility Large language models (LLMs) such as BERT, T5, GPT-3, and others are exceptional resources for applying general knowledge to your specific problem. Being able to frame a new task as a question for a language model (zero-shot learning), or showing it a few…

In this paper, accepted at ICLR 2022, Chris and team at Stanford outline a new principled evaluation framework for comparing slice detection methods, then introduce a new technique motivated by our discoveries that outperforms existing methods by double digits.