13 Hits in 4.0 sec

RMIT at the 2017 TREC CORE Track

Rodger Benham, Luke Gallagher, Joel Mackenzie, Tadele Tedla Damessie, Ruey-Cheng Chen, Falk Scholer, Alistair Moffat, J. Shane Culpepper
2017 Text Retrieval Conference  
INTRODUCTION e TREC 2017 CORE Track 1 is a re-run of the classic TREC ad hoc search evaluation campaign, with the vision of establishing new methodologies for creating IR test collections. e previous TREC  ...  newswire ad hoc task was the 2004 Robust Track, where the emphasis was on improving the e ectiveness of poorly performing topics in previous tracks [16] . e TREC CORE 2017 track reuses the Robust 2004  ... 
dblp:conf/trec/BenhamGMDCSMC17 fatcat:4vy6iperp5cwpkfpmdsm6qyufq

RMIT at the 2018 TREC CORE Track

Rodger Benham, Luke Gallagher, Joel Mackenzie, Binsheng Liu, Xiaolu Lu, Falk Scholer, J. Shane Culpepper, Alistair Moffat
2018 Text Retrieval Conference  
It forms the basis of web search, question-answering, and a new generation of virtual assistants being developed by several of the largest so ware companies in the world.  ...  In this report, we continue our exploration of the importance of multiple expressions of information needs.  ...  [3] , and this was used for the RMIT CORE runs in 2017.  ... 
dblp:conf/trec/BenhamGML0SCM18 fatcat:wo453fdgnnbnxnwwv3hba6f7pm

RMITB at TREC COVID 2020 [article]

Rodger Benham, Alistair Moffat, J. Shane Culpepper
2020 arXiv   pre-print
These user query variations have been exploited in past TREC CORE tracks to contribute diverse, highly-effective runs in offline evaluation campaigns with the goal of producing reusable test collections  ...  In this paper, we document the query fusion runs submitted to the first and second round of TREC COVID, using ten queries per topic created by the first author.  ...  Code Code and query variations to reproduce experiments are available at rmit-ir/rmitb-trec-covid.  ... 
arXiv:2011.04830v1 fatcat:nyy5uc6mubhd3foidnmfatquvy

Overview of the TREC 2020 deep learning track [article]

Nick Craswell, Bhaskar Mitra, Emine Yilmaz, Daniel Campos
2021 arXiv   pre-print
This is the second year of the TREC Deep Learning Track, with the goal of studying ad hoc ranking in the large training data regime.  ...  We evaluate using single-shot TREC-style evaluation, to give us a picture of which ranking methods work best when large data is available, with much more comprehensive relevance labeling on the small number  ...  Our official labels are more comprehensive, covering a large number of results per query, and labeled on a four point scale at NIST.  ... 
arXiv:2102.07662v1 fatcat:ydpxzcongzfenn6uiwcpywm7ce

Overview of the NTCIR-13 We Want Web Task

Cheng Luo, Tetsuya Sakai, Yiqun Liu, Zhicheng Dou, Chenyan Xiong, Jingfang Xu
2017 NTCIR Conference on Evaluation of Information Access Technologies  
In this paper, we provide an overview of the NTCIR We Want Web (WWW) task, which comprises the Chinese and the English subtasks. The WWW task is a classical ad-hoc textual retrieval task.  ...  In this overview paper, we describe the task details, data and evaluation methods, as well as the report on the official results.  ...  This is in sharp contrast to the early TRECs where there were only a few tracks, where the ad hoc track (a set of new topics run against a static document collection) was at the core.  ... 
dblp:conf/ntcir/0001S0DXX17 fatcat:x62n432idngutdnwkbrdcqxgou

Overview of the 2019 Open-Source IR Replicability Challenge (OSIRRC 2019)

Ryan Clancy, Nicola Ferro, Claudia Hauff, Jimmy Lin, Tetsuya Sakai, Ze Zhong Wu
2019 Annual International ACM SIGIR Conference on Research and Development in Information Retrieval  
In total, 13 teams from around the world submitted 17 images, most of which were designed to produce retrieval runs for the TREC 2004 Robust Track test collection.  ...  The Open-Source IR Replicability Challenge (OSIRRC 2019), organized as a workshop at SIGIR 2019, aims to improve the replicability of ad hoc retrieval experiments in information retrieval by gathering  ...  ACKNOWLEDGEMENTS We would like to thank all the participant who contributed Docker images to the workshop. This exercise would not have been possible without their efforts.  ... 
dblp:conf/sigir/Clancy0HLSW19a fatcat:qi5ug6dgejakvoipfa5hsgqo3m

TREC 2017 Common Core Track Overview

James Allan, Donna Harman, Evangelos Kanoulas, Dan Li, Christophe Van Gysel, Ellen M. Voorhees
2017 Text Retrieval Conference  
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

A2A: a platform for research in biomedical literature search

Maciej Rybinski, Sarvnaz Karimi, Vincent Nguyen, Cecile Paris
2020 BMC Bioinformatics  
Our setup is guided by the NIST setup of the relevant TREC evaluation tasks in genomics, clinical decision support, and precision medicine.  ...  Our experiments report well-known information retrieval metrics such as precision at a cutoff of ranked documents.  ...  Acknowledgements We acknowledge the contributions of our colleagues in the previous versions of the A2A system: Falk Scholer (RMIT University), Sara Falamaki (ex-CSIRO), and Brian Jin (CSIRO).  ... 
doi:10.1186/s12859-020-03894-8 pmid:33349237 fatcat:dy45nsg2mvf3nlwrxf4s5wpe3a

Towards Efficient and Effective Query Variant Generation

Rodger Benham, J. Shane Culpepper, Luke Gallagher, Xiaolu Lu, Joel Mackenzie
2018 Biennial Conference on Design of Experimental Search & Information Retrieval Systems  
For many of the classic TREC test collections, these approaches were used in many of the top performing retrieval systems.  ...  We show that our new end-to-end search system approaches the state-of-the-art in effectiveness while still being efficient in practice.  ...  The second external corpus is referred to as NYT and is from the TREC 2017 CORE Track, containing articles published in the New York Times from 1987-2007.  ... 
dblp:conf/desires/BenhamCGLM18 fatcat:f35puf5levhxzpi5yvqzdk6awi

Conversational Search – A Report from Dagstuhl Seminar 19461 [article]

Avishek Anand, Lawrence Cavedon, Matthias Hagen, Hideo Joho, Mark Sanderson, Benno Stein
2020 arXiv   pre-print
The seminar also had three social events during the program.  ...  This report provides the executive summary, overview of invited talks, and findings from the seven working groups which cover the definition, evaluation, modelling, explanation, scenarios, applications  ...  On the basis of these results, some specific challenges to the design of conversational search systems are identified.  ... 
arXiv:2005.08658v1 fatcat:ekkylrysezfkfcwkuk5ynrcwki

Conversational Search (Dagstuhl Seminar 19461)

Avishek Anand, Lawrence Cavedon, Hideo Joho, Mark Sanderson, Benno Stein
2020 Dagstuhl Reports  
The seminar also had three social events during the program.  ...  This report provides the executive summary, overview of invited talks, and findings from the seven working groups which cover the definition, evaluation, modelling, explanation, scenarios, applications  ...  Any opinions, findings, and conclusions described here are the authors and do not necessarily reflect those of the sponsors.  ... 
doi:10.4230/dagrep.9.11.34 dblp:journals/dagstuhl-reports/AnandCJSS19 fatcat:ctqyitsfifcbbecio5dnx2i62y

Dagstuhl Reports, Volume 6, Issue 1, January 2016, Complete Issue [article]

at how a population can efficiently explore a plateau region, while the third problem looks at how a population can solve a problem despite a very large of noise.  ...  Surveillance is directed at a target population, and "mass" means the surveillance is directed at the vast majority of the targeted population. This can be done by both governments and companies.  ...  performance by running a single core at the maximum voltage or multiple cores at nominal level for a very short time period.  ... 
doi:10.4230/dagrep.6.1 fatcat:vq74ezrwifbkhex6twvtdzbpaa

Annual Report 2018
国立情報学研究所 平成30年度(2018年度)年報

専門分野 組合せ最適化,パラメータ化計算量 所属学会・学会役職 ACM SIGACT 受賞 1) 岩田陽一,重村卓人:PACE 2018: Track A 1st place, Track B 2nd place (2018.08) 2) Takuya Akiba, Kentaro Imajo, Hiroaki Iwami, Yoichi Iwata, Toshiki Kataoka, Naohiro  ...  21st International Conference on Artificial Intelligence and Statistics (AISTATS) (2018.04) 4) Daisuke Hatano and Yuichi Yoshida: "Computational Aspects of the Preference Cores of Supermodular Two-Scenario  ... 
doi:10.20736/0000001316 fatcat:ag6okeeknjeoxglo6j6yylm55y