Travelled to:
1 × France
1 × Norway
1 × Singapore
1 × Spain
1 × Switzerland
1 × United Kingdom
3 × China
3 × USA
Collaborated with:
E.Yilmaz B.Carterette J.A.Aslam V.Pavlu S.E.Robertson K.Dai P.D.Clough M.Sanderson S.Savev J.Allan N.Craswell H.Fang M.L.Paramita T.Xia D.Zhang Y.Du P.Metrikov
Talks about:
evalu (10) effect (4) retriev (3) score (3) queri (3) user (3) distribut (2) behavior (2) system (2) measur (2)
Person: Evangelos Kanoulas
DBLP: Kanoulas:Evangelos
Contributed to:
Wrote 20 papers:
- CIKM-2014-YilmazKC #evaluation #retrieval
- Effect of Intent Descriptions on Retrieval Evaluation (EY, EK, NC), pp. 599–608.
- CIKM-2012-CarteretteKY #behaviour #evaluation #variability
- Incorporating variability in user behavior into systems based evaluation (BC, EK, EY), pp. 135–144.
- ECIR-2012-DaiPKA
- Extended Expectation Maximization for Inferring Score Distributions (KD, VP, EK, JAA), pp. 293–304.
- SIGIR-2012-CarteretteKY #development #evaluation #metric
- Advances on the development of evaluation measures (BC, EK, EY), pp. 1200–1201.
- SIGIR-2012-RobertsonK #evaluation #information retrieval #on the #topic
- On per-topic variance in IR evaluation (SER, EK), pp. 891–900.
- SIGIR-2012-RobertsonK12a #ad hoc #evaluation #on the #realtime #retrieval
- On real-time ad-hoc retrieval evaluation (SER, EK), pp. 1119–1120.
- CIKM-2011-CarteretteKY #behaviour #effectiveness #evaluation #simulation
- Simulating simple user behavior for system effectiveness evaluation (BC, EK, EY), pp. 611–620.
- SIGIR-2011-KanoulasCCS #multi
- Evaluating multi-query sessions (EK, BC, PDC, MS), pp. 1053–1062.
- SIGIR-2011-KanoulasSMPA #algorithm #ranking #scalability #set
- A large-scale study of the effect of training set characteristics over learning-to-rank algorithms (EK, SS, PM, VP, JAA), pp. 1243–1244.
- SIGIR-2010-CarteretteKPF #design #reuse
- Reusable test collections through experimental design (BC, EK, VP, HF), pp. 547–554.
- SIGIR-2010-CarteretteKY #evaluation #information retrieval #low cost
- Low cost evaluation in information retrieval (BC, EK, EY), p. 903.
- SIGIR-2010-KanoulasDPA #modelling #robust
- Score distribution models: assumptions, intuition, and robustness to score manipulation (EK, KD, VP, JAA), pp. 242–249.
- SIGIR-2010-RobertsonKY #precise
- Extending average precision to graded relevance judgments (SER, EK, EY), pp. 603–610.
- SIGIR-2010-SandersonPCK #evaluation #metric #question
- Do user preferences and evaluation measures line up? (MS, MLP, PDC, EK), pp. 555–562.
- CIKM-2009-KanoulasA #empirical
- Empirical justification of the gain and discount function for nDCG (EK, JAA), pp. 611–620.
- ECIR-2009-CarterettePKAA #query
- If I Had a Million Queries (BC, VP, EK, JAA, JA), pp. 288–300.
- SIGIR-2009-AslamKPSY #documentation #effectiveness #performance #ranking
- Document selection methodologies for efficient and effective learning-to-rank (JAA, EK, VP, SS, EY), pp. 468–475.
- SIGIR-2008-CarterettePKAA #evaluation #query
- Evaluation over thousands of queries (BC, VP, EK, JAA, JA), pp. 651–658.
- SIGIR-2008-YilmazKA #performance
- A simple and efficient sampling method for estimating AP and NDCG (EY, EK, JAA), pp. 603–610.
- VLDB-2005-XiaZKD #on the
- On Computing Top-t Most Influential Spatial Sites (TX, DZ, EK, YD), pp. 946–957.