In the past year or so, our team has been working on TF-Ranking, open-source scalable TensorFlow library for learning-to-rank models. Excited to share it today with the research community!

European Summer School lecture on tips for doing research in IR ciir.cs.umass.edu/downloads/essi…

Weize Kong will be presenting (pre-recorded video w/ live Q&A) our joint work on "Learning to Cluster Documents into Workspaces Using Large Scale Activity Logs" (research.google/pubs/pub49265/) at the upcoming ADS #KDD2020 session on Content Recommendation & Retrieval Systems.

Introducing the *CIIR Talk Series*, a biweekly event; open to everyone. We live stream the presentations and publish the recorded talks (with a consent from the presenters). If you are interested in learning more about the events or joining the talks, see the thread 👇

The summary of our participation in the TREC COVID challenge is now out (arxiv.org/abs/2010.00200). Our team, unique_ptr, achieved SOTA performance in Rounds 4 & 5 of the challenge. Key take-aways:

I am looking for multiple Ph.D. students to join my lab Khoury College of Computer Sciences Northeastern U. in Fall of 2021 to work on exciting computer vision problems. *Deadline is Dec 15 and GRE is not required*. See details at jianghz.me/opportunities. Please help RT!

And we also used the same user activity data to learn to cluster documents in our recent KDD paper research.google/pubs/pub49265/

Please RT! If you're looking for a PhD position in a world leading information retrieval research lab, the Center for Intelligent Information Retrieval (CIIR) at UMass CS2 is hiring multiple students for Fall 2021. Deadline: Dec. 15. Questions? drop me an email. SIGIR Students

Congrats to my students! Our pretraining for IR method looks promising!

Our #WSDM2021 paper "Improving Cloud Storage Search with User Activity" is now available at research.google/pubs/pub50003/

We are very happy to announce WIT: Wikipedia-Based Image Text Dataset, a large multimodal multilingual dataset. Google AI ai.googleblog.com/2021/09/announ…

Excited that Chen Qu will present our work "Natural Language Understanding with Privacy-Preserving BERT" at #CIKM2021 today. research.google/pubs/pub50636/ Joint work w/ Chen Qu Liu Yang Mingyang (Michael) Zhang Michael Bendersky Marc Najork

Delighted to share that our paper titled "Learning Discrete Representations via Constrained Clustering for Effective and Efficient Dense Retrieval" has won the #WSDM2022 Best Paper Award! 🥳🥳🥳 Congrats to Jingtao Zhan and all co-authors! link: wsdm-conference.org/2022/timetable…

I’ll give an oral presentation for this work tomorrow at the 10am search & information retrieval session. Come join us! #kdd2022

Our team at Google Research is looking for a student researcher (research intern) to work on Information Retrieval + Large Language Model. Please share your CV with [email protected] and apply via careers.google.com/jobs/results/?…, if interested. Thanks! #intern2023 #research #ir #llm

For decades, retrievers have been optimized for human users. However, LLM may have different preferences wrt ranking & selection cf. humans. Join us 4 PM today #ACL2024NLP poster session to explore how to bridge such preference gaps for RAG, arxiv.org/pdf/2401.06954 w/ Zixuan Ke

Join us at 4pm today #ACL2024NLP poster session for our work “PRewrite: Prompt Rewriting with Reinforcement Learning” arxiv.org/pdf/2401.08189 w/ Spurthi Amba Hombaiah