Online Testing for Learning To Rank: Interleaving

If you have read Part 1 of this blog post, you should know by now how many fantastic things can be done with online testing! In particular, the advantages that interleaving brings with respect to A/B testing, but you are still waiting for the answer to a question: how to implement it? Let's see together … Continue reading Online Testing for Learning To Rank: Interleaving

The Importance of Online Testing in Learning to Rank – Part 1

You have just trained a learning to rank model and you now want to know how it performs. You can start by looking at the evaluation parameters returned by the train on the test set, but you are still not sure of which will be the impact in using it in a real website. This … Continue reading The Importance of Online Testing in Learning to Rank – Part 1

Introducing Weighted Synonyms in Apache Lucene/Solr

This blog post is about our latest contribution to the Apache Lucene/Solr project:introducing the ability of assigning different weights to synonyms.This contribution aims to help users that deal with complex synonyms dictionaries where it's important to associate a numerical weight to each of them, for example to boost the ones that are more important in … Continue reading Introducing Weighted Synonyms in Apache Lucene/Solr

London Information Retrieval Meetup February

After the very warm reception of the first year, the fourth London Information Retrieval Meetup is approaching (11/02/2020) and we are excited to add more details about our speakers and talks!The event is free and you are invited to register : https://www.eventbrite.com/e/london-information-retrieval-meetup-february-2020-tickets-89056738101 Our first speaker is Anna Ruggero, one of our R&D software engineers: Anna … Continue reading London Information Retrieval Meetup February

Road to Rated Ranking Evaluator Enterprise

It was the spring of 2018, Andrea was strenuously working on a customer project, continuously tuning search configurations and checking the ground truth for certain queries manually. That was pretty much the standard at the time, the brilliant Quepid[1] from our friends at Open Source Connection helped in some use cases, but there was nothing … Continue reading Road to Rated Ranking Evaluator Enterprise

Entity Search with graph embeddings – Part 4 – Evaluation and conclusion

This is the last post of the Entity Search with graph embeddings serie. In Part 2 and Part 3 we illustrated the core of the dissertation describing in detail the implementation of our solution pipeline. In this final part we will see some evaluation measures and results. We will draw some conclusions explaining which were … Continue reading Entity Search with graph embeddings – Part 4 – Evaluation and conclusion

Entity Search with graph embeddings – Part 3 – Documents and retrieval

In this post we want to get to the heart of the process of virtual documents creation. As we explained in Part 1, these documents are essential for the retrieval phase and for its performances. This part of the pipeline is, indeed, the one where we create our own approaches in many different versions. Summarizing … Continue reading Entity Search with graph embeddings – Part 3 – Documents and retrieval