All Stories

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