Forschungskolloquium des IWS: Explainable Artificial Intelligence and Data Programming
Vortrag, 19. April 2022
Der (zu gründende) Forschungsschwerpunkt Knowledge Discovery am Institut für Informationswissenschaft freut sich, das durch die Corona-Pandemie ausgesetzte Forschungskolloquium des IWS wieder anbieten zu können. Es findet als hybride Veranstaltung sowohl vor Ort als auch in Zoom statt.
Auf einen Blick
Björn Engelmann: Combining Explainable Artificial Intelligence (XAI) and Data Programming (DP) to make Relation Extraction explainable and debuggable
VortragWann?
- 19. April 2022
- 15.15 Uhr bis 17.30 Uhr
-
in meinen Kalender übertragen
BEGIN:VCALENDAR VERSION:2.0 PRODID:-//hacksw/handcal//NONSGML v1.0//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:EUROPE/BERLIN BEGIN:DAYLIGHT TZOFFSETFROM:+0100 TZOFFSETTO:+0200 TZNAME:CEST DTSTART:19700329T020000 RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU END:DAYLIGHT BEGIN:STANDARD TZOFFSETFROM:+0200 TZOFFSETTO:+0100 TZNAME:CET DTSTART:19701025T030000 RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU END:STANDARD END:VTIMEZONE BEGIN:VEVENT LOCATION:Campus Südstadt\, Claudiusstr. 1\, Raum 158 oder per Zoom: Meeting ID: 83506753468\, Kennwort 167256 DESCRIPTION: SUMMARY:Björn Engelmann: Combining Explainable Artificial Intelligence (XAI) and Data Programming (DP) to make Relation Extraction explainable and debuggable DTSTART;TZID=EUROPE/BERLIN:20220419T151500 DTEND;TZID=EUROPE/BERLIN:20220419T173000 DTSTAMP:20241213T222925 UID:675ca73590f35 END:VEVENT END:VCALENDAR
Wo?
Campus Südstadt, Claudiusstr. 1, Raum 158
oder per Zoom: Meeting ID: 83506753468, Kennwort 167256
https://th-koeln.zoom.us/j/83506753468
Veranstaltungsreihe
Forschungskolloquium Informationswissenschaft
ReferentIn
Björn Engelmann Kontakt
Anmeldung
keine Anmeldung notwendig
Weitere Informationen
Explainable Artificial Intelligence (XAI) is a growing field of research that seeks to explain black-box behavior. Typically, the goal is to make model decisions interpretable by providing explanations or visualizations for specific model decisions. Research also looks at how to correct flawed decisions by updating the model.
In the research field of Data Programming (DP), methods are developed to annotate large amounts of data using heuristics. However, these heuristics usually have to be defined by subject matter experts, which requires technical know-how. Our approach aims to combine methods from the research fields of XAI and DP to make Relation Extraction explainable and debuggable.
Vortragssprache
deutsch