BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pyconde-pydata-berlin-2023//speaker//DVRPY9
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-berlin-2023-VHNJ37@pretalx.com
DTSTART;TZID=CET:20230419T140000
DTEND;TZID=CET:20230419T143000
DESCRIPTION:Models in Natural Language Processing are fun to train but can 
 be difficult to deploy. The size of their models\, libraries and necessary
  files can be challenging\, especially in a microservice environment. When
  services should be built as lightweight and slim as possible\, large (lan
 guage) models can lead to a lot of problems. With a recent real-world use 
 case as an example\, which runs productively for over a year and in 10 dif
 ferent languages\, I will walk you through my experiences with deploying N
 LP models. What kind of pitfalls\, shortcuts\, and tricks are possible whi
 le bringing an NLP model to production?\n\nIn this talk\, you will learn a
 bout different ways and possibilities to deploy NLP services. I will speak
  briefly about the way leading from data to model and a running service (w
 ithout going into much detail) before I will focus on the MLOps part in th
 e end. I will take you with me on my past journey of struggles and success
 es so that you don’t need to take these detours by yourselves.
DTSTAMP:20260421T235627Z
LOCATION:B09
SUMMARY:Bringing NLP to Production (an end to end story about some multi-la
 nguage NLP services) - Larissa Haas\, Jonathan Brandt
URL:https://pretalx.com/pyconde-pydata-berlin-2023/talk/VHNJ37/
END:VEVENT
END:VCALENDAR