A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is
In this report, we discuss the experiments we conducted for the TREC 2017 Common Core Track. ... For the second round of submissions, we cra ed a user study to measure the impact of interaction mechanisms on technology assisted review and completed an initial version of the study with 10 users and ... 1 INTRODUCTION e task of TREC 2017 Common Core Track 1 is an ad-hoc retrieval of documents for a set of topics from the New York Times dataset 2 . ...dblp:conf/trec/ZhangAGGSCG17 fatcat:mlaghknxajfj3cqshy2z32ysx4
11.1 hours judging documents (13.2 minutes per topic). e same CAL implementation was used for relevance assessments for the MRG UWaterloo submission in TREC Common Core Track 2017  . ese assessments ... SUBMITTED RUNSWe submi ed four runs to the Common CORE track 2018 for evaluation. All these runs were manual runs. ...dblp:conf/trec/AbualsaudCGGGRZ18 fatcat:sil23zs46zg2vmlopai63dbk6a
of the 250 Common Core topics. ... Our primary goal was to create, with less effort, a set of relevance assessments ("qrels") comparable to the official Common Core Track qrels (cf. [12, 2]). ... For these 50 topics, we formed the union of the three corpora from TREC 2004, TREC 2005, and Common Core 2017. ...dblp:conf/trec/GrossmanC17 fatcat:l5qrmbbapreqdc2nabbuisksoy
in alphabetical order. 1 Participants have the opportunity to train their systems over the TREC 2004 Robust track (which, to some extend, alters the participants task to a routing task, i.e. fixed queries ... For the Common Core track, we used k = 10 and X = 100. ... Introduction The primary goal of the TREC Common Core track is three-fold: (a) bring the information retrieval community back into a traditional ad-hoc search task; (b) attract a diverse set of participating ...dblp:conf/trec/AllanHKLGV17 fatcat:sj7iwu27wbfwnm2wbenlgbxmfm