Paul Piwek

Artificial Intelligence · 2004–2019

A researcher in the Science corpus: 5 papers; trusts 28 researchers and is trusted by 8 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 15 citations into it; #17,403 of 35,345 by trust here, #23,077 by citations
• Statistics and Probability — 15 citations into it
• Evaluation & Benchmarks — 13 citations into it; #1,436 of 3,147 by trust here, #2,275 by citations
• Natural Language Processing — 13 citations into it
• Management Science and Operations Research — 6 citations into it
• Experimental and Cognitive Psychology — 5 citations into it

Whom Paul Piwek trusts overall

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

1. Klaus Krippendorff
2. J. Fleiss
3. Daniel Kahneman
4. Geoff Norman
5. Kultar Singh
6. Julian J. Faraway
7. Spencer E. Harpe
8. Daniel M. McNeish
9. Albert Gatt
10. J. Landis

Who trusts Paul Piwek overall

1. Elizabeth Clark
2. Cheng-Han Chiang
3. Asli Celikyilmaz
4. K. Dörr
5. Emiel Krahmer
6. Neslihan Iskender
7. Chris van der Lee
8. Hung-yi Lee

Papers from Paul Piwek's perspective

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

1. Bleu: a Method for Automatic Evaluation of Machine Translation
2. Framing Image Description as a Ranking Task: Data, Models and Evaluation Metrics
3. Content Analysis: An Introduction to Its Methodology
4. RankME: Reliable Human Ratings for Natural Language Generation
5. Measuring nominal scale agreement among many raters.
6. How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation
7. On Using Language
8. Likert scales: how to (ab)use them (Medical Education)
9. Comparing Automatic Evaluation Measures for Image Description
10. Resolving the 50‐year debate around using and misusing Likert scales (Medical Education)

Their papers

• The use of rating and Likert scales in Natural Language Generation human evaluation tasks: A review and some recommendations (2019) — 61 citations
• Agreement is overrated: A plea for correlation to assess human evaluation reliability (2019) — 45 citations
• Rethinking the Agreement in Human Evaluation Tasks (2018) — 54 citations
• 'Proximal' and 'distal' in language and cognition : Evidence from deictic demonstratives in Dutch (2008) — 104 citations
• Natural Language Generation (2004) — 234 citations