BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/St_Johns
BEGIN:DAYLIGHT
DTSTART:20260308T030000
TZOFFSETFROM:-0430
TZOFFSETTO:-0330
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:NDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20251102T010000
TZOFFSETFROM:-0330
TZOFFSETTO:-0430
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:NST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20251115T203758Z
UID:A2027D8E-71A2-41FE-92A8-E2E74609C8CD
DTSTART;TZID=America/St_Johns:20251105T100000
DTEND;TZID=America/St_Johns:20251105T110000
DESCRIPTION:Abstract: Unstructured documents often come with embedded struc
 tured data. Representing valuable and structured information as tables is 
 popular in health\, financial\, and many domains. However\, manual extract
 ion of structured information from documents typically costs tremendous ti
 me and labor\, motivating the need for a system for automating the process
 . After such tables have been extracted\, the data can be used for a wide 
 variety of tasks such as question answering and various “down-stream” 
 analytics tasks. In this talk\, we will discuss how to leverage ground-bre
 aking pre-trained language models (e.g.\, BERT\, ChatGPT) to develop tools
  for automated table extraction from various types of documents. We will p
 resent different applications from cancer registry reporting\, cancer care
 \, and psychiatry hospitalization prediction.\n\nSpeaker(s): Raymond Ng\n\
 nRoom: CSF-1302\, Bldg: Core Science Facility \, 45 Arctic Avenue\, St. Jo
 hn's\, Newfoundland and Labrador\, Canada
LOCATION:Room: CSF-1302\, Bldg: Core Science Facility \, 45 Arctic Avenue\,
  St. John's\, Newfoundland and Labrador\, Canada
ORGANIZER:mhamilton@mun.ca
SEQUENCE:20
SUMMARY:Health Care Applications with Natural Language Processing
URL;VALUE=URI:https://events.vtools.ieee.org/m/509868
X-ALT-DESC:Description: <br /><p class="MsoNormal" style="margin-bottom: 24
 .0pt\; text-align: left\;" align="left"><strong><span lang="EN-US" style="
 font-size: 9.5pt\; mso-bidi-font-size: 10.0pt\; font-family: 'Verdana'\,sa
 ns-serif\; color: #131313\;">Abstract</span></strong><span lang="EN-US" st
 yle="font-size: 9.5pt\; mso-bidi-font-size: 10.0pt\; font-family: 'Verdana
 '\,sans-serif\; color: #131313\;">: </span><span style="font-size: 9.5pt\;
  mso-bidi-font-size: 10.0pt\; font-family: 'Verdana'\,sans-serif\; color: 
 #131313\; mso-ansi-language: EN-CA\;">Unstructured documents often come wi
 th embedded structured data. Representing valuable and structured informat
 ion as tables is popular in health\, financial\, and many domains. However
 \, manual extraction of structured information from documents typically co
 sts tremendous time and labor\, motivating the need for a system for autom
 ating the process. After such tables have been extracted\, the data can be
  used for a wide variety of tasks such as question answering and various &
 ldquo\;down-stream&rdquo\; analytics tasks. In this talk\, we will discuss
  how to leverage ground-breaking pre-trained language models (e.g.\, BERT\
 , ChatGPT) to develop tools for automated table extraction from various ty
 pes of documents. We will present different applications from cancer regis
 try reporting\, cancer care\, and psychiatry hospitalization prediction.&n
 bsp\;</span></p>\n<p class="MsoNormal" style="margin-bottom: 24.0pt\; text
 -align: left\;" align="left">&nbsp\;</p>
END:VEVENT
END:VCALENDAR