Practical Tricks for Bootstrapping Information Extraction Pipelines


In this presentation, I will build on Ines Montani's keynote, "Applied NLP in the Age of Generative AI," by demonstrating how to create an information extraction pipeline. This pipeline will include a text classifier to filter relevant articles, an entity recognizer to identify names and numeric data, and a relation extraction system developed with the help of a large language model (LLM) powered human-in-the-loop annotation process. The talk will focus on using the spaCy NLP library and the Prodigy annotation tool, although the principles discussed will also apply to other frameworks.

Key Takeaways:

  • Learn how to construct an information extraction pipeline using text classification, entity recognition, and relation extraction.
  • Discover the integration of LLM-powered human-in-the-loop annotation processes to enhance relation extraction systems.
  • Understand the practical application of the spaCy NLP library and Prodigy annotation tool in building NLP solutions.


Book Tickets
Workshop Tickets are almost sold out! Grab them before they are gone!




Download agenda

We use cookies essential for this site to function well. Please click to help us improve its usefulness with additional cookies. Learn about our use of cookies in our Privacy Policy & Cookies Policy.

Show details