BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pyconde-pydata-berlin-2023//talk//B7PCUR
BEGIN:VTIMEZONE
TZID:Europe/Berlin
BEGIN:DAYLIGHT
DTSTART:20220417T000000
TZNAME:CEST
TZOFFSETFROM:+0200
TZOFFSETTO:+0200
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20221030T030000
RDATE:20231029T030000
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20230326T030000
RDATE:20240331T030000
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:How to baseline in NLP and where to go from there - Tobias Sterbak
DTSTART;TZID=Europe/Berlin:20230417T151000
DTEND;TZID=Europe/Berlin:20230417T154000
DTSTAMP:20260809T015834Z
UID:pretalx-pyconde-pydata-berlin-2023-B7PCUR@pretalx.com
DESCRIPTION:In this talk\, we will explore the build-measure-learn paradig
 m and the role of baselines in natural language processing (NLP). We will 
 cover the common NLP tasks of classification\, clustering\, search\, and n
 amed entity recognition\, and describe the baseline approaches that can be
  used for each task. We will also discuss how to move beyond these baselin
 es through weak learning and transfer learning. By the end of this talk\, 
 attendees will have a better understanding of how to establish and improve
  upon baselines in NLP.
LOCATION:A03-A04
URL:https://pretalx.com/pyconde-pydata-berlin-2023/talk/B7PCUR/
END:VEVENT
END:VCALENDAR