BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.4.5//EN
TZID:America/Los_Angeles
X-WR-TIMEZONE:America/Los_Angeles
BEGIN:VEVENT
UID:407@escience.washington.edu
DTSTART;TZID=America/Los_Angeles:20261103T163000
DTEND;TZID=America/Los_Angeles:20261103T172000
DTSTAMP:20261029T205356Z
URL:https://escience.washington.edu/events/uw-data-science-and-ai-seminar-
 todd-nobles/
SUMMARY:UW Data Science and AI Seminar: Todd Nobles
DESCRIPTION:\nPlease join us for a UW Data Science Seminar featuring UW Soc
 iology PhD student Todd Nobles on Tuesday\, November 3rd from 4:30 to 5:20
  p.m. PT. The seminar will be held in HCK 132.\n“Recovering Names from t
 he Archives: Vision-Language Models for OCR and Named Entity Recognition 
 ”\nAbstract: This talk shares preliminary results from work as part of t
 he Puyallup Family Data Reclamation Project\, which in collaboration with 
 the Puyallup Tribal Historic Preservation Department\, aims to digitize hi
 storical boarding school archival records and make them searchable and acc
 essible to those researching their family history. These archival document
 s contain a mixture of faded typewriting\, cursive handwriting\, tables\, 
 forms\, and handwritten notes\, presenting significant challenges for trad
 itional optical character recognition (OCR) techniques. As part of the eSc
 ience AI Accelerator\, I worked with Curtis Atkisson to test the feasibili
 ty of using the vision-language capabilities of large language models to b
 oth extract text from these documents and perform named entity recognition
  (NER) to identify the individuals within the corpus. I will present early
  results comparing two OCR approaches\, using olmOCR and Gemma 4\, paired 
 with different NER techniques\, including traditional NLP models like Flai
 r and LLM-based extraction with Gemma 4. By evaluating these outputs again
 st human-annotated ground truths\, I offer initial insights into the poten
 tial of these models to quickly and cost-effectively extract information f
 rom large and varied archival collections.\n\nSpeaker Bio: Todd Nobles is 
 a PhD student in Sociology at the University of Washington and a CSDE Data
  Science and Demography T32 trainee. His dissertation examines how environ
 mental hazards shape residential mobility and migration as well as the soc
 ial and political implications of these shifting populations. In other res
 earch\, he works with digitizing historical administrative data to study t
 he life-course consequences of internment on German and Austrian Americans
  during World War I.\n\n\n\nThe 2026-2027 seminars will be held in person\
 , and are free and open to the public.\n\n\n\n\n\n\n
ATTACH;FMTTYPE=image/jpeg:https://escience.washington.edu/wp-content/uploa
 ds/2026/10/headshot-2.jpeg
END:VEVENT
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:STANDARD
DTSTART:20261101T010000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
END:STANDARD
END:VTIMEZONE
END:VCALENDAR