suzan boosted

researcher in NL or B (or keen on visiting Amsterdam):

Better register soon: dir2019.nl may run out of capacity, so if you are not quick...

suzan boosted

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

arxiv.org/abs/1807.03819

suzan boosted

Slides for all lectures at the course:

informagus.nl/events/siks-ir-2

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

suzan boosted
suzan boosted

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"

arxiv.org/abs/1910.00896

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

Data: arxiv.org/abs/1910.00896

Vacancies!

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

ifs.tuwien.ac.at/dossier/phd_p

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

w/ @arjen @leifos

suzan boosted

Ik heb vandaag een bachelordiploma uitgereikt aan een student die geboren is in het jaar dat ik eindexamen deed.

suzan boosted
suzan boosted
suzan boosted

Register now for the ⚡ lightning ⚡ talk edition. 30 Euro for highlights of last year's Dutch-Belgian Information Retrieval research.

dir2019.nl/registration.html

Published in PLOS ONE:

"The reach of commercially motivated junk news on Facebook" by Peter Burger, Soeradj Kanhai, Alexander Pleijter, and Suzan Verberne
journals.plos.org/plosone/arti

suzan boosted
suzan boosted

I believe conferences should have a "telepresence chair". is getting there (and I expect them to)

chi2019.acm.org/for-attendees/

suzan boosted
suzan boosted

Of 18 algorithms presented at top-level conferences only 7 could be reproduced with reasonable effort. 6 can often be outperformed with comparably simple heuristic. The last did not consistently outperform a well-tuned non-neural linear ranking method. arxiv.org/abs/1907.06902

suzan boosted

Krisztian Balog's attempt to do fully transparent movie recommendation. Very interesting and original research:

doi.org/10.1145/3331184.333121

suzan boosted

Donna Harman's "Information Retrieval: The early years" can be downloaded for free until 17 July.

nowpublishers.com/article/Deta

Show more
Mastodon

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.