We are delighted to announce the seventeenth edition of the London Information Retrieval Meetup and this time it will be an Hybrid event!
As usual, the meetup will be free and aimed at those who are passionate about Information Retrieval and professionals who are curious to explore and discuss the latest trends in the field.
The event will be structured with 2 technical talks, each talk will be followed by a Q&A and, in the end, we are going to have a networking session.
[open door for people joining the event in presence – 6:00 PM]
After a short welcome & latest news speech from our Founder Alessandro Benedetti, we will proceed to the talks.
[Talks start at 6:30]
Word2Vec Model To Generate Synonyms on the Fly in Apache Lucene: Story of a Contribution
An open source contribution is a satisfying experience because multiple people and companies potentially use your piece of code. Furthermore, it allows you to improve the features you want or add some new features. This is not always as easy as it seems: you work with a community of people with different experiences and different ideas and you have to deal with everybody and agree on compromises if you want to get your job done.
We added a new feature in Apache Lucene to generate synonyms on the fly using the Word2Vec model. In this talk, we see the full story from when we decided to start a new contribution until we finally had everything merged.
Software engineer passionate about high-performance data structures and algorithms.
He likes studying and experimenting new technologies trying to improve the state of art.
Autoregressive Knowledge Retrieval
When the world moved from static word representations to contextual language models NLP changed forever. I believe we are close to a similar revolution in information retrieval (IR). The dominating paradigms in IR are dense (e.g., DPR) and sparse (e.g., BM25), both static approaches in their essence. In this talk, I’ll present a third approach: autoregressive retrieval. Join the talk to know more. 🙂
Fabio is Co-Founder & CTO at Samaya AI, building an AI-powered knowledge-discovery platform. Before that he was a Researcher at FAIR and Thomson Reuters, focusing on representing, gathering, extracting, using, reasoning on and creating world knowledge using AI.