We are delighted to announce the twenty-first 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-presence
Location: Gladwin Tower, nine elms point sw8 2fs London [see on google maps]
Date: 11th July 2024 | open doors from 6:15 PM (GMT+1)
// online
Location: Zoom [You will receive the link after the registration]
Date: 11th July 2024 | 6:30-8:30 PM (GMT+1)
// LONDON INFORMATION RETRIEVAL MEETUP
PROGRAM
The event will be structured around 2 technical talks, each followed by a Q&A session. The event will end with a networking session.
> Open doors from 6:15 PM GMT+1 (in-presence)
> 6:30 GMT+1 open doors for virtual attendees
> 6:30-6:45 PM Welcome from Alessandro Benedetti (Director @ Sease)
> 6:45-7:30 PM FIRST TALK
> 7:30-8:15 PM SECOND TALK
> 8:15-9:00 PM Networking session + buffet
// first talk
Search UX SUX: how we fail to put search engine functionality in the hands of users and what to do about it
// second talk
Hybrid Search With Apache Solr Reciprocal Rank Fusion
Vector-based search gained incredible popularity in the last few years: Large Language Models fine-tuned for sentence similarity proved to be quite effective in encoding text to vectors and representing some of the semantics of sentences in a numerical form.
These vectors can be used to run a K-nearest neighbour search and look for documents/paragraphs close to the query in a n-dimensional vector space, effectively mimicking a similarity search in the semantic space (Apache Solr KNN Query Parser).
Although exciting, vector-based search nowadays still presents some limitations:
– it’s very difficult to explain (e.g. why is document A returned and why at position K?)
– it doesn’t care about exact keyword matching (and users still rely on keyword searches a lot)
Hybrid search comes to the rescue, combining lexical (traditional keyword-based) search with neural (vector-based) search.
So, what does it mean to combine these two worlds?
It starts with the retrieval of two sets of candidates:
– one set of results coming from lexical matches with the query keywords
– a set of results coming from the K-Nearest Neighbours search with the query vector
The result sets are merged and a single ranked list of documents is returned to the user.
Reciprocal Rank Fusion (RRF) is one of the most popular algorithms for such a task.
This talk introduces the foundation algorithms involved with RRF and walks you through the work done to implement them in Apache Solr, with a focus on the difficulties of the process, the distributed support(SolrCloud), the main components affected and the limitations faced, all updated to the latest days.
The audience is expected to learn more about this interesting approach, the challenges in it and how the contribution process works for an Open Source search project as complex as Apache Solr.
Alessandro Benedetti
FOUNDER @ SEASE
APACHE LUCENE/SOLR COMMITTER
APACHE SOLR PMC MEMBER
Senior Search Software Engineer, his focus is on R&D in Information Retrieval, Information Extraction, Natural Language Processing, and Machine Learning.
He firmly believes in Open Source as a way to build a bridge between Academia and Industry and facilitate the progress of applied research.
