I am confused: At the business meeting, the executive committee claimed that "all ACM SIGIR publications are permanent open access on the DL", but that is clearly not the case, see my attempt to download Bruce Croft's SIGIR 2019 keynote paper.

All ACM SIGIR publications and permanent open access in the ACM digital library!

2020 Test of time award goes to Hao Ma et al. SIGIR 2009 "Learning to recommend with social trust ensemble"

2020 Test of time award Honorable Mention 2: Guihong Cao et al. SIGIR 2008

2020 Test of time award Honorable Mention 1: Georges Dupret and Benjamin Piwowarski, SIGIR 2008

Best short paper: Shi Yu et al. "Few-short conversational query rewriting"

2020 Short paper honorable mention: Jianxin Chang: "Bundle recommendation with graph convolutional networks"

Best paper: Marco Mornik et al. "Controlling fairness and bias in dynamic learning to rank"

Honorable mention best paper award : Fan Zhang et al. "Models vs Satisfaction"

Why do we need deep learning, when neural nets can already approximate any function?

Going to find out how deep learning works for Information Retrieval with Dacheng Tao.

Norbert Fuhr's recommendations for gaining scientific knowledge from experiments:

1. Do not use MRR or MAP;
2. Instead of relative improvements, regard the effect size!
3. For multiple significance tests, use a correction, such as Bonferoni or Tukey's HSD (NB comparing only to the 2nd best method does not help!)
4. There are no significant improvements for re-usable test collections! (hypotheses have to be formulated before the work)

Nice! Harrie Oosterhuis presenting a new counter-factual learning to rank approach that takes the item display policy (top-k cut-off) into account.

Eye opener. Johanne Trippas brought a game of cards with faces of Turing award winners: They're all male! 😮

Nazlia Goharian shows that we, the IR community, are not doing that well on gender equality!

Show more

The "unofficial" Information Retrieval Mastodon Instance.

Goal: Make idf.social a viable and valuable social space for anyone working in Information Retrieval and related scientific research.

Everyone welcome but expect some level of geekiness on the instance and federated timelines.