Another #IR reproducibility study that is worth having a look at: Simple Techniques for Cross-Collection Relevance Feedback.
Nice results for the Radboud IR team at #ECIR2020:
Reproducibility paper "Which BM25 Do You Mean? A Large-Scale Reproducibility Study of Scoring Variants" by Chris Kamphuis, Leonid Boytsov, Jimmy Lin and @arjen
Portugal in spring, nice reward for hard work!
Excellent reasons for academia-industry collaboration by @arjen, with unexpected end...
On Entities and Evaluation https://prismo.xyz/posts/a82901b4-35e5-48ac-be2d-f041e46293cf
Dutch researchers: Here's your reminder that since 2015, it is perfectly legal to make ALL your publications open access after a reasonable time:
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.