Paul Thomas

Artificial Intelligence · 2008

A researcher in the Science corpus: 1 paper; trusts 3 researchers and is trusted by 1 researcher here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 6 citations into it; #33,050 of 35,345 by trust here, #24,417 by citations
• Evaluation & Benchmarks — 6 citations into it
• Information Retrieval & Search — 6 citations into it
• Information Systems — 5 citations into it; #7,934 of 8,771 by trust here, #5,501 by citations

Whom Paul Thomas trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Emine Yilmaz

Who trusts Paul Thomas overall

1. William R. Hersh

Papers from Paul Thomas's perspective

Ordered by how strongly the researchers Paul Thomas trusts endorse each paper. Same corpus, a different order for every researcher.

1. Retrieval evaluation with incomplete information
2. A statistical method for system evaluation using incomplete judgments
3. Variations in relevance judgments and the measurement of retrieval effectiveness
4. IR evaluation methods for retrieving highly relevant documents
5. A simple and efficient sampling method for estimating AP and NDCG
6. Estimating average precision with incomplete and imperfect judgments (International Conference on Information and Knowledge Management)
7. Relevance assessments and retrieval system evaluation
8. A Coefficient of Agreement for Nominal Scales
9. Nonparametric statistics for the behavioral sciences
10. Squibs and Discussions: The Kappa Statistic: A Second Look (International Conference on Computational Logic)

Their papers

• Relevance assessment: are judges exchangeable and does it matter (2008) — 216 citations