Forschungskolloquium des IWS: Reproducibility in Information Retrieval Research
Vortrag, 10. Januar 2023
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
Timo Breuer: Reproducibility in Information Retrieval Research – Towards a More Principled Approach of System-Oriented Evaluations and User-Oriented External Validations
VortragWann?
- 10. Januar 2023
- 15.15 Uhr bis 16.30 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:Timo Breuer: Reproducibility in Information Retrieval Research – Towards a More Principled Approach of System-Oriented Evaluations and User-Oriented External Validations DTSTART;TZID=EUROPE/BERLIN:20230110T151500 DTEND;TZID=EUROPE/BERLIN:20230110T163000 DTSTAMP:20240901T011146 UID:66d3a332d7888 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
Timo Breuer, M.Sc.
Anmeldung
keine Anmeldung notwendig
Weitere Informationen
In this talk, I will present some outcomes of my dissertation project and it is the first dry run of my final defense. My dissertation is about reproducible IR research and how system-oriented reproducibility experiments can be evaluated in a more principled way. Related to reproducibility is the question of external validity, i.e., how reproducible are the results in a different context? As part of this project, the user's influence is considered a key component that creates a different context. By shifting the experimental focus to a more user-oriented direction, it will be outlined how external validity can be evaluated by user simulations and, finally, in living lab experiments with real users.
Vortragssprache
englisch