We are delighted to announce the 25th London Information Retrieval Meetup & AI, a free evening event aimed at enthusiasts and professionals curious to explore and discuss the latest trends in the field.
This time the Meetup is Hybrid, with a live event in London, being streamed online on Zoom!
in LONDON
Location:
BCS London Headquarters,
Ground Floor, 25
Copthall Avenue
EC2R 7BP [Google Maps]
Date: 24th November 2025 | open doors from 6:00 PM
VIRTUAL
Location: Zoom [You will receive the link after the registration]
Date: 24th November 2025 | 6:15 PM (GMT)
LONDON INFORMATION RETRIEVAL & AI MEETUP
PROGRAM
The event will be structured around 3 technical talks, each followed by a Q&A session. The event will end with a networking session.
> Open doors from 6:00 PM GMT (in-presence)
> 6:15 GMT open doors for virtual attendees
- 6:15-6:30 PM Welcome from Alessandro Benedetti (Director @ Sease)
- 6:30 PM FIRST TALK
“Using Tensor and Rank Profile Math to Combine Dense and Sparse Signals”
Radu Gheorghe – Software Engineer @ Vespa - 7:15 SECOND TALK
“From Infection Prevention to Knowledge Extraction: Showcasing Information Retrieval in the Medical Domain”
Gregor Donabauer | PhD student and Research Officer @University of Regensburg - 8:00 PM THIRD TALK
“Professional Search in the Age of Large Language Models”
Samy Ateia | PhD student @University of Regensburg + Freelance Software Engineer
> Networking session + buffet
FIRST talk
Using Tensor and Rank Profile Math to Combine Dense and Sparse Signals
We’ll take a top-down approach to retrieval: which signals matter most (dense/sparse vectors, lexical…) and we’ll look at how to combine them in various ways (including normalizing) to get good quality.
In Vespa, we’d recommend modeling relevance with tensor math wherever possible: it’s much faster and potentially easier to maintain. But we’ll also look at combining higher-level signals (e.g., from document fields) into rank profiles. Rank profiles are Vespa’s relevance language, exposing features like inheritance and 2-stage re-ranking.
To exemplify, we’ll show open-source sample applications that deal with both dense vectors (ColPali) and sparse (LLM-generated user preferences).
The speaker
Radu Gheorghe
Software Engineer @ Vespa.ai
Radu has been in the search space for many years, mainly on Elasticsearch, Solr, OpenSearch, and, more recently, Vespa.ai. Helps users with both the relevance and the operations side of retrieval.
Enjoys education in all its forms (training, blog posts, books, conferences…) and got the chance to be involved in all of them.
second talk
From Infection Prevention to Knowledge Extraction: Showcasing Information Retrieval in the Medical Domain
This talk explores applications of Information Retrieval (IR) in the medical domain through two examples. (1) Outbreak Detection through Graph-Based Infection Prediction: We address the detection of outbreaks of multi-resistant bacteria in
hospitals by modelling potential spread patterns via patient movements as a graph.
A Graph Neural Network (GNN) is trained on this data to predict potential infection events, enabling proactive measures to prevent outbreaks. (2) Information Extraction from Medical Documents: Motivated by a use case in the urological domain, we focus on extracting and organizing high-evidence information from medical documents. Using recent advances in the field, we demonstrate how large language models (LLMs) and clustering techniques can be applied to identify and group high-evidence information nuggets, providing valuable input for experts in the age of information overload.
The speaker
Gregor Donabauer
PhD student and Research Officer @University of Regensburg
I am a PhD student and research officer at the Chair of Information Science at the University of Regensburg (Germany). I previously also worked as a research assistant at the University of Milano-Bicocca (Italy). I hold both a Bachelor’s degree in Information Science/Information Systems and a Master’s degree in Information Science from the University of Regensburg. My research interests focus on Natural Language Processing and Graph Machine Learning, particularly in the areas of Information Retrieval and applications in the medical domain. In addition, I serve as an elected committee member of the British Computer Society’s Information Retrieval Specialist Group (BCS IRSG) and as the editor of the IRSG Informer newsletter.
third talk
Professional Search in the Age of Large Language Models
What challenges and chances present themselves when we try to automate professional search tasks with current LLM based AI systems? We will look at biomedical systematic reviews and question answering. How can we achieve close expert oversight and integration while improving both speed, transparency and quality?
The speaker
Samy Ateia
PhD student @University of Regensburg + Freelance Software Engineer
Samy Ateia is a PhD candidate in the Information Science Group at the University of Regensburg (since March 2023) and a software engineer with professional experience since 2016, working freelance since 2019. He specializes in search engine integration and information retrieval (IR).
