BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pyconde-pydata-berlin-2023//talk//VHNJ37
BEGIN:VTIMEZONE
TZID:Europe/Berlin
BEGIN:DAYLIGHT
DTSTART:20220419T000000
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:Bringing NLP to Production (an end to end story about some multi-l
 anguage NLP services) - Larissa Haas\, Jonathan Brandt
DTSTART;TZID=Europe/Berlin:20230419T140000
DTEND;TZID=Europe/Berlin:20230419T143000
DTSTAMP:20260818T174001Z
UID:pretalx-pyconde-pydata-berlin-2023-VHNJ37@pretalx.com
DESCRIPTION:Models in Natural Language Processing are fun to train but can
  be difficult to deploy. The size of their models\, libraries and necessar
 y files can be challenging\, especially in a microservice environment. Whe
 n services should be built as lightweight and slim as possible\, large (la
 nguage) 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 di
 fferent languages\, I will walk you through my experiences with deploying 
 NLP models. What kind of pitfalls\, shortcuts\, and tricks are possible wh
 ile bringing an NLP model to production?\n\nIn this talk\, you will learn 
 about different ways and possibilities to deploy NLP services. I will spea
 k briefly about the way leading from data to model and a running service (
 without going into much detail) before I will focus on the MLOps part in t
 he end. I will take you with me on my past journey of struggles and succes
 ses so that you don’t need to take these detours by yourselves.
LOCATION:B09
URL:https://pretalx.com/pyconde-pydata-berlin-2023/talk/VHNJ37/
END:VEVENT
END:VCALENDAR