BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//programme.europython.eu//europython-2024//speaker//YJQTQ
 N
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-europython-2024-PSLA9J@programme.europython.eu
DTSTART;TZID=CET:20240712T112000
DTEND;TZID=CET:20240712T115000
DESCRIPTION:In natural language processing\, embeddings are crucial for und
 erstanding textual data. In this talk\, we’ll explore sentence embedding
 s and their application in dialog systems. We'll focus on a use case invol
 ving the classification of dialogs.\n\nWe'll demonstrate the necessity of 
 sentence transformers for this problem\, specifically utilizing one of the
  top-performing small-sized sentence transformers. We will show how to fin
 e-tune this model with both labeled and unlabeled dialog data\, using the 
 SentenceTransformers Python framework.\n\nThis talk is practical\, packed 
 with easy-to-follow examples\, and aimed at building intuition around this
  topic. While some basic knowledge of Transformers would be beneficial\, i
 t is not required. Newcomers are also welcome.
DTSTAMP:20260612T024423Z
LOCATION:Terrace 2A
SUMMARY:Representation is King: The Journey to Quality Dialog Embeddings - 
 Adam Zíka
URL:https://programme.europython.eu/europython-2024/talk/PSLA9J/
END:VEVENT
END:VCALENDAR