BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pyconde-pydata-2024//talk//RLCLBB
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-pyconde-pydata-2024-RLCLBB@pretalx.com
DTSTART;TZID=CET:20240423T141000
DTEND;TZID=CET:20240423T144000
DESCRIPTION:In 2023\, the field of NLP was again flurried -- the appearing 
 of powerful closed- and opens-source LLMs opened new possibility for texts
  processing. However\, many questions about these models usability for typ
 ical NLP tasks are still open. One of them is quite simple -- if we want a
  classification model for some task\, can we rely on LLMs or is it still b
 etter to fine-tune an own model? It might be easier to obtain some classif
 ier for English\, but what if my target language is not so resource-rich? 
 In this presentation\, the main "recipes" how to obtain the best text clas
 sifier depending on the language and data availability will be described.
DTSTAMP:20260718T151729Z
LOCATION:B07-B08
SUMMARY:How to Do Monolingual\, Multilingual\, and Cross-lingual Text Class
 ification in April\, 2024 - Daryna Dementieva
URL:https://pretalx.com/pyconde-pydata-2024/talk/RLCLBB/
END:VEVENT
END:VCALENDAR