Gabriel Damour on digital experiences. Explore my blog.
The goal of this review is to compare the quality of new semantic-based algorithms using embeddings versus traditional term-based search ranking algorithms to retrieve good content: The traditional is Okapi BM25, an the new ones are Elastic Learned Sparse EncodeR (ELSER, retrieval model trained by Elastic.co) and all-MiniLM-L6-v2 from sbert.net. Adding Google because it is a good reference point. Which one works for what type of query. Part 2 details the experience and present the findings.
31 Dec 2023 - by Gabriel
The goal of this review is to compare the quality of new semantic-based algorithms using embeddings versus traditional term-based search ranking algorithms to retrieve good content. The traditional is Okapi BM25, an the new ones are the models Elastic Learned Sparse EncodeR (ELSER) and all-MiniLM-L6-v2 from sbert.net. Adding Google because it is a good reference point. Which one works for what type of query. Part 1 presents the background.
31 Oct 2023 - by Gabriel
Why and How to run your own Large language model on your traditional cloud provider like AWS.
31 Aug 2023 - by Gabriel
In this post I’ll describe my experience re-installing android on my phone and “regain” control on it.
31 May 2019 - by Gabriel
In 2018 Google and Facebook Artificial Intelligence research labs have again heavily invested into neural networks: This is still the most researched approach to IA, concentrated approximately 2/3 of their research effort based on the number of publications. A trend that is likely to remain in 2019.
31 Dec 2018 - by Gabriel
Sydney has more than 200 electricity substations built in the 1920s-1930s by Sydney Municipal Council. I randomly discovered a few of them over the few years I have been living here. In this post I’m sharing a few personal photos of what some of those substations look like the city today.
18 Sep 2018 - by Gabriel
The My Health Record opt-out period has started the 16th of July in Australia and will last until the 15th of October. We have 3 months to make an informed decision about our health electronic data. In this post I’m sharing a 5 reasons why you should opt-out.
31 Jul 2018 - by Gabriel
Reviewing an ARM-based, ie not a traditional x86 cloud based hosting provider: Scaleway.
30 Jun 2018 - by Gabriel
Uncover in details the highly critical Drupal vulnerability nicknamed “drupalgeddon 2” that was released March and April 2018
31 May 2018 - by Gabriel
I’m sharing in this post my interest for a report written by Alan Turing in 1948: ‘Intelligent machinery’. This report contains several founding and yet still modern ideas about artificial intelligence.
30 Apr 2018 - by Gabriel
This post is describing my experience when running a bitcoin full node on an ubuntu container.
31 Dec 2017 - by Gabriel