All Stories

  1. Browsing and Searching Metadata of TREC
  2. Human Preferences as Dueling Bandits
  3. Too Many Relevants
  4. TREC Deep Learning Track: Reusable Test Collections in the Large Data Regime
  5. On the Quality of the TREC-COVID IR Test Collections
  6. Coopetition in IR research
  7. Coopetition in IR Research
  8. TREC-COVID
  9. On Building Fair and Reusable Test Collections using Bandit Techniques
  10. Evaluating Evaluation Measure Stability
  11. On the Behavior of PRES Using Incomplete Judgment Sets