The IRLab at U. of Amsterdam, w/ Mohammad Aliannejadi @maliannejadi, Evangelos Kanoulas @ekanou, Maarten Marx, Maarten de Rijke @mdr, Andrew Yates @andrewyates
Amsterdam
Joined October 2010
- Tweets1.8K
- Following174
- Followers2K
- Likes1.7K
The IRLab at the University of Amsterdam retweeted
🚨🚨🚨Tutorial Recording Alert!🚨🚨🚨
We just released the recording of our tutorial titled:
Unbiased Learning to Rank: On Recent Advances in the Foundations and Applications
youtu.be/fcqCkjgOnJ8
Originally presented at the #SIGIR2023, #FIRE2023 and #WSDM2024 conferences.
Join us for Search Engines Amsterdam this Friday at 4pm CEST! @snbruch (Pinecone) and @HansiZeng (UMass) will join us and discuss recent innovations in search indexing for dense retrieval and in generative IR.
Sign up here 👇
meetup.com/sea-search-engine…
The IRLab at the University of Amsterdam retweeted
With @maliannejadi, we presented our poster this week at @naacl. Excited to share our latest findings and engage with the NLP community #NAACL2024 #NLPresearch.
Glad to share that our paper: "Context Does Matter: Implications for Crowdsourced Evaluation Labels in Task-Oriented Dialogue Systems" has been accepted at #NAACL2024! with @maliannejadi and @mdr.
Join us next Friday, June 28th, for our last SEA meet-up before the summer break! 🎉
@snbruch (Pinecone) and @HansiZeng (UMass Amherst) will discuss recent innovations in search indexing for dense retrieval and in scaling generative IR.
Sign up here 👉 meetup.com/de-DE/sea-search-…
Another SEA 🌊 meetup in May? Yes 🎉! This Thursday at 13:00 CET, we will host @peterpaws (University of Pittsburgh) at IRLab for a talk on "User Control for Personalized Information Access".
Sign up now 👉: meetup.com/de-DE/sea-search-…
Join us at the IRLab this Friday for Search Engines Amsterdam 🌊. @olivierjeunen will visit us and take a critical look at evaluating recommender systems using nDCG.
Sign up here 👉: meetup.com/de-DE/sea-search-…
SEA 🌊 is back! Join us on Friday, May 17th, when @olivierjeunen takes a critical look at evaluating recommender systems using nDCG!
Sign up here 👉: meetup.com/de-DE/sea-search-…
The IRLab at the University of Amsterdam retweeted
🧵We just released a large-scale reproducibility effort on unbiased learning-to-rank (ULTR). It turned out that ULTR did not work as intended ... or at least that its success depends on how your measure success.
Many thanks to Philipp Hager, @JMRenders, Onno Zoeter, @mdr
ALT A comparison of unbiased learning-to-rank techniques on Baidu-ULTR: a massive dataset of annotated results from Baidu's search engine.
The IRLab at the University of Amsterdam retweeted
🚀 Eager to improve speed and performance in LLM-based re-ranking?
Explore our #SIGIR2024 @SIGIRConf long paper “Ranked List Truncation for Large Language Model-based Re-Ranking” w/ @NegarEmpr @arian_ask @maliannejadi @mdr
Preprint: arxiv.org/abs/2404.18185
Thread 👇 1/4 – at Amsterdam, The Netherlands
Interested in improving our understanding of climate impact? In appraising the growing literature on climate impact? Tell us where research on IR for climate impact should go. Submit 2-4 pp abstract to SIGIR'24 workshop on IR for Climate Impact. DL: May 9. sites.google.com/view/ir-for…
The IRLab at the University of Amsterdam retweeted
1/4 I'm happy to announce that we at @irlab_amsterdam will organize the next edition of the European Summer School in Information Retrieval (ESSIR) @essir_eu on July 1-5 at the University of Amsterdam.
Early registration deadline: May 31.
More info: 2024.essir.eu
Join us tomorrow at 5pm for Search Engines Amsterdam 🌊, with talks by @ArthurCamara and @arian_ask
about using LLMs for data augmentation in IR! 🎉
Register here: meetup.com/sea-search-engine…
Search Engines Amsterdam 🌊 is back! Next Friday, we host two great talks by @ArthurCamara and @arian_ask on using LLMs for data augmentation in IR.
Register now and join us next week: meetup.com/de-DE/sea-search-…
The IRLab at the University of Amsterdam retweeted
1/4 Interested in fine-tuning open-source LLMs to generate relevance judgments?
Check out our paper “Query Performance Prediction using Relevance Judgments Generated by Large Language Models” w/ @NegarEmpr @arian_ask @maliannejadi @mdr
Paper at: arxiv.org/abs/2404.01012 – at Amsterdam, The Netherlands
The IRLab at the University of Amsterdam retweeted
🚀 Can we rely on LLMs’ internal knowledge to answer complex questions? 🚀
In our recent work with @maliannejadi, we propose a method for generating multiple queries to cover different aspects of the user’s information needs.
The paper is available:
arxiv.org/abs/2403.19302
The IRLab at the University of Amsterdam retweeted
Listening to Andrew Yates @andrewyates (University of Amsterdam) giving an in-person @ir_glasgow seminar at @GlasgowCS entitled “An encoder-centric view of neural retrieval” #GlasgowIRTalk
Thrilled to share that we have multiple papers and workshops authored by members of #IRLab accepted at #SIGIR2024! 🎉 Looking forward to attending the conference in DC.
irlab.science.uva.nl/2024/03…
The IRLab at the University of Amsterdam retweeted
Our reproducibility paper "Ranked List Truncation: From Retrieval to Re-ranking" w/ @NegarEmpr @arian_ask @maliannejadi @mdr got accepted at #SIGIR2024 @SIGIRConf
We show query-specific re-ranking depths can optimize effectiveness/efficiency trade-offs in LLM-based re-ranking – at Glasgow, Scotland
The IRLab at the University of Amsterdam retweeted
Happy to share that our full paper "Going Beyond Popularity and Positivity Bias: Correcting for Multifactorial Bias in Recommender Systems" with @_Jin_Huang_, @HarrieOos, @herkevanhoof, and @mdr has been accepted at #SIGIR2024.
