BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pyconde-pydata-berlin-2023//speaker//DLCVJ
 F
BEGIN:VTIMEZONE
TZID:Europe/Berlin
BEGIN:DAYLIGHT
DTSTART:20220418T000000
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 Chatbots work – We need to talk! - Yuqiong Weng\, Katrin Rei
 ninger
DTSTART;TZID=Europe/Berlin:20230418T110500
DTEND;TZID=Europe/Berlin:20230418T113500
DTSTAMP:20260812T151553Z
UID:pretalx-pyconde-pydata-berlin-2023-AKXXQD@pretalx.com
DESCRIPTION:Chatbots are fun to use\, ranging from simple chit-chat (“Ho
 w are you today?”) to more sophisticated use cases like shopping assista
 nts\, or the diagnosis of technical or medical problems. Despite their mos
 tly simple user interaction\, chatbots must combine various complex NLP co
 ncepts to deliver convincing\, intelligent\, or even witty results. \n\nWi
 th the advancing development of machine learning models and the availabili
 ty of open source frameworks and libraries\, chatbots are becoming more po
 werful every day and at the same time easier to implement. Yet\, depending
  on the concrete use case\, the implementation must be approached in speci
 fic ways. In the design process of chatbots it is crucial to define the la
 nguage processing tasks thoroughly and to choose from a variety of techniq
 ues wisely. \n\nIn this talk\, we will look together at common concepts an
 d techniques in modern chatbot implementation as well as practical experie
 nces from an E-mobility bot that was developed using the Rasa framework.
LOCATION:B05-B06
URL:https://pretalx.com/pyconde-pydata-berlin-2023/talk/AKXXQD/
END:VEVENT
END:VCALENDAR