"Pretrained Transformers for Text Ranking: BERT and Beyond" with Rodrigo Nogueira and Andrew Yates - it started on June 18, 2020 and culminates here with the official publication... Enjoy! institutional subscribers: morganclaypool.com/doi/10.2200/S0… retail orders: morganclaypoolpublishers.com/catalog_Orig/p…

📢Tomorrow is the official book launch party of Pretrained Transformers for Text Ranking: BERT and Beyond, by Jimmy Lin, Rodrigo Nogueira, and Andrew Yates at SEA. Open for everyone 🌍! Sign up for the last spots and have a chance to win the book📚 meetup.com/SEA-Search-Eng…

We are excited that CLPsych 2022 will be collocated with #NAACL2022. For more info on important dates and the shared task, check our website clpsych.org

I'm really excited by this episode about Spider in the Neural IR Talks podcast @ZetaVector! Sergi Castella i Sapé and Andrew Yates - many thanks for considering our work, it was a pleasure listening 🤗

Excited to share my first ACM SIGIR 2022 paper "Zero-shot Embedding Contextualization for Conversational Search" 🎉🎉🥳 w/ Andrew Yates and @ekanou arxiv.org/abs/2204.10613 More details 👇

I'm presenting "Zero-Shot Query Contextualization for Conversational Search" tomorrow at #SIGIR2022 (poster session 13/07 15.30-17.00). Would be happy to chat about it if you're in Madrid! (joint work with @ekanou Andrew Yates)

We release the public beta for bnb-int8🟪 for all Hugging Face 🤗models, which allows for Int8 inference without performance degradation up to scales of 176B params 📈. You can run OPT-175B/BLOOM-176B easily on a single machine 🖥️. You can try it here: docs.google.com/document/d/1Jx… 1/n

This is joint work with Sean MacAvaney and Andrew Yates

We are proud to have the following paper authored by members of IRLab accepted at SIGIR 2023🎉 irlab.science.uva.nl/2023/04/06/irl…

📢CLPsych Shared Task '24 🗓️Registration deadline: December 10th ℹ️If you are interested in working with LLMs for "explaining stuff" or in #NLProc for mental health, check out the CLPsych page! clpsych.org/shared-task-20… Team:Dana Atzil-Slonim @jennycwchim Dimitris Gkoumas Maria Liakata

I'm hiring a postdoc to work on topics in neural IR. Interested? Learn more and apply here: vacatures.uva.nl/UvA/job/Postdo…

1/4 I'm happy to announce that we at The IRLab at the University of Amsterdam will organize the next edition of the European Summer School in Information Retrieval (ESSIR) ESSIR on July 1-5 at the University of Amsterdam. Early registration deadline: May 31. More info: 2024.essir.eu

Interested in speeding up approximate retrieval over learnt sparse embeddings of up to 12x w.r.t. the winning methods of the Big ANN 2023 Sparse Track challenge? Check this out: arxiv.org/abs/2404.18812. Long paper @ #SIGIR2024 with @snbruch, cosimorulli, Rossano Venturini

CLPsych 2025 is happening 🎉 and will be collocated with NAACL. The first Call for Papers is out. Please consider submitting and help us spread the word. clpsych.org

Join us on 27 Feb in Amsterdam for the ELLIS workshop on Representation Learning and Generative Models for Structured Data sites.google.com/view/rl-and-gm…

I'm excited about this line of work, as it paves the way towards more effective and lexically grounded representations for negated and set-compositional queries! Many thanks to my co-authors for their support and constructive feedback Andrew Yates @ekanou #IR #NLP #research

Ever wonder how test-time compute would do in retrieval? 🤔 introducing ✨rank1✨ rank1 is distilled from R1 & designed for reranking. rank1 is state-of-the-art at complex reranking tasks in reasoning, instruction-following, and general semantics (often 2x RankLlama 🤯) 🧵

Check out our latest work, Video-ColBERT, an efficient late interaction approach for video retrieval! Recently accepted at #CVPR2025

🚨 IT'S HERE! 🚨 The Eval Leaderboard is now LIVE! 🏆💻 Our video retrieval collection stumps most pre-trained models. See if you can build a better system! eval.ai/web/challenges…

🚨Wouldn’t it be nice if your agentic search system could reason over all your docs? ✨Introducing Rank-K, a listwise reranker that benefits from test-time compute and long-context! Rank-K sets a new SoTA for reasoning-based reranking, without reasoning chains from other models.