BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
DTSTART:20230312T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20221106T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230217T051245Z
UID:62A8D72B-C03E-41D4-BC82-1FEA749F0071
DTSTART;TZID=America/New_York:20230216T200000
DTEND;TZID=America/New_York:20230216T213000
DESCRIPTION:This talk explores an interesting approach for text retrieval: 
 a community-based approach called "coopetitions."\n\nCoopetitions are acti
 vities in which competitors cooperate for a common good. Community evaluat
 ions such as the Text REtrieval Conference (TREC\, trec.nist.gov) are prot
 otypical examples of coopetitions in information retrieval\, and they have
  now been part of the field for more than thirty years. This longevity and
  the proliferation of shared evaluation tasks suggest that\, indeed\, the 
 net impact of community evaluations is positive.\n\nCoopetitions can impro
 ve effectiveness for a retrieval task by setting up a collaborative struct
 ure: establishing a research cohort and constructing the infrastructure (i
 ncluding problem definition\, test collections\, scoring metrics\, and res
 earch methodology) that the participants need to make progress on the task
 . They can also facilitate technology transfer and amortize the infrastruc
 ture costs. Yet these benefits only accrue when the infrastructure is a go
 od abstraction of the real task. Information retrieval's test collection p
 aradigm is becoming increasingly untenable as corpus size grows and search
  engine effectiveness improves. This talk will review what we have learned
  about test-collection-based evaluation of search engines from TREC and ex
 amine the prospects of search evaluation in the future.\n\nSpeaker(s): Ell
 en Voorhees\, \n\nRoom: Room 105\, Bldg: Computer Science Building\, Princ
 eton University\, Princeton\, New Jersey\, United States\, 08544\, Virtual
 : https://events.vtools.ieee.org/m/345494
LOCATION:Room: Room 105\, Bldg: Computer Science Building\, Princeton Unive
 rsity\, Princeton\, New Jersey\, United States\, 08544\, Virtual: https://
 events.vtools.ieee.org/m/345494
ORGANIZER:dmancl@acm.org
SEQUENCE:1
SUMMARY:Coopetition in Information Retrieval Research
URL;VALUE=URI:https://events.vtools.ieee.org/m/345494
X-ALT-DESC:Description: <br /><p>This talk explores an interesting approach
  for text retrieval: a community-based approach called "coopetitions."</p>
 \n<p>Coopetitions are activities in which competitors cooperate for a comm
 on good. Community evaluations such as the Text REtrieval Conference (TREC
 \, trec.nist.gov) are prototypical examples of coopetitions in information
  retrieval\, and they have now been part of the field for more than thirty
  years. This longevity and the proliferation of shared evaluation tasks su
 ggest that\, indeed\, the net impact of community evaluations is positive.
 </p>\n<p>Coopetitions can improve effectiveness for a retrieval task by se
 tting up a collaborative structure: establishing a research cohort and con
 structing the infrastructure (including problem definition\, test collecti
 ons\, scoring metrics\, and research methodology) that the participants ne
 ed to make progress on the task. They can also facilitate technology trans
 fer and amortize the infrastructure costs. Yet these benefits only accrue 
 when the infrastructure is a good abstraction of the real task. Informatio
 n retrieval's test collection paradigm is becoming increasingly untenable 
 as corpus size grows and search engine effectiveness improves. This talk w
 ill review what we have learned about test-collection-based evaluation of 
 search engines from TREC and examine the prospects of search evaluation in
  the future.</p>
END:VEVENT
END:VCALENDAR