Only registered attendees will have access to the session links. Please register through the Sched platform using the email address associated with your Zoom account. Visit the 2022 LD4 Conference site for more information.

Session times are shown in Eastern Daylight Time (EDT) by default. Use the Timezone dropdown on the right to select your preferred timezone.

Back To Schedule
Monday, July 11 • 9:00am - 12:00pm
Visualizing and Training Machine Learning Models with Sinopia Linked Data

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

An update to last year's workshop, this workshop provides participants the opportunity to explore Sinopia's Linked Data resources through a machine-learning lens. The workshop will have four sections. The first section will be an introduction to Jupyter Notebooks, harvesting RDF from Sinopia's API, and analyzing and visualizing the RDF using Pandas. The second section takes the Panda dataframes from the first-section and then build a custom spaCy Named Entity Recognition pipeline for tagging descriptions with FAST subject headings. The third section will use HuggingFace transformers for NER and summarization pipelines using PyTorch. The final section focuses on broader machine learning challenges and will introduce participants to Model Cards and Data Statements for describing the work they did during the workshop.

avatar for Jeremy Nelson

Jeremy Nelson

Software Engineer, Stanford University Libraries

Monday July 11, 2022 9:00am - 12:00pm EDT