Google has made “substantial” contributions to some of the most notorious climate deniers in Washington despite its insistence that it supports political action on the climate crisis.

David @graus provides compelling scientific evidence that the filter bubble, if it exists at all, benefits diversity more than it hurts diversity.

Universal Transformers: a transformer approach by Mostafa Dehghani and colleagues that also uses a recurrent feedback loop. Very interesting.

"Give orange me give eat orange me eat orange give me eat orange give me you"

Nim Chimpsky (1973 -- 2000)

Slides for all lectures at the course:

Here, you also find the information for the group experiment of this afternoon.

Full house for the Course for PhD students in Utrecht, NL.

Faegheh Hasibi @fhasibi presenting the lecture on Entity Oriented Search now.

Morning program included Claudia Hauff on Learning to Rank and other Machine learning for , and Hinda Haned on FAT* related topics such as algorithmic bias.

"The merits of Universal Language Model Fine-tuning for Small Datasets - a case with Dutch book reviews"

Work by Benjamin van der Burgh @LIACS, evaluating the effectiveness of ULMFiT for small training sets


View from the office: de-googlify internet (ty @djoerd) and Martha's PixelPrivacy poster, subliminal biasing our students against the surveillance economy :-)


15 fully-funded PhD Positions on Domain-Specific Search (EU Marie Curie Action project)

I am hiring for project 6 and 7, addressing transparency and explainability in legal search.

w/ @arjen @leifos

The merits of Universal Language Model Fine-tuning for Small Datasets -- a case with Dutch book reviews. (arXiv:1910.00896v1 [cs.IR])

Come do your PhD with me at Spinque in Utrecht, NL, on the topic of Professional Search:

Fully funded, with three secondments in Vienna (Allan Hanbury), Milan (Gabriella Pasi) and Tennessee (Diane Kelly).

See the Marie-Curie ITN DOSSIER website for 14 more cool projects, all over Europe, including two in Leiden with Suzan Verberne.

Show more

The "unofficial" Information Retrieval Mastodon Instance.

Goal: Make 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.