Prodigy in 2023: LLMs, task routers, QA and pluginsWe have made a ton of new updates in Prodigy this year with v1.12, v1.13, and v1.14 releases. So we decided to write a post about them.
Half hour of labeling power: Can we beat GPT?PyData NYCLarge Language Models (LLMs) offer a lot of value for modern NLP and can typically achieve surprisingly good accuracy on predictive NLP tasks. But can we do even better than that? In this workshop we show how to use LLMs at development time to create high-quality datasets and train specific, smaller, private and more accurate models for your business problems.
The triangulation of ethical leader signals using qualitative, experimental, and data science methodsBanks, Ross, Toth, Tonidandel, Goloujeh, Dou, Wesslen (2022)This additional text was labeled by the same coding team using Prodigy, [...] a flexible user interface tool built on top of spaCy, a leading open source library in python for natural language processing. We created a spaCy end‐to‐end project workflow including package versioning, data pre‐processing, data ingestion into a database, annotation sessions using Prodigy’s user interface, model training, model evaluation, python packaging, and visual app for testing the model.
How the Guardian approaches quote extraction with NLPA case study of the Guardian's spaCy-Prodigy workflow to modularize quote extraction for content creation. This study includes iterative annotation guidelines and custom interface functionality.
Deploying a Prodigy cloud service for Posh’s financial chatbotsA Prodigy case study of Posh AI's production-ready annotation platform and custom chatbot annotation tasks for banking customers.
Can You Verifi This? Studying Uncertainty and Decision-Making About MisinformationKarduni, Wesslen, Santhanam, Cho, Volkova, Arendt, Shaikh, Dou (2018)HCI interface to identify misinformation on social media using spaCy for NER.
