A Synonym By Any Other Name: From Alt. Labels to Knowledge Graphs
When people say they have 'synonyms' in their search engine, it can turn out to mean a lot of different things...
An Introduction to Search Quality
When considering improvements to search in a product or application it is necessary to have a vision of overall quality, which is a combination of three key areas: relevance, experience, and performance. This article explains all three at a high level and why they matter as a whole, and offers some tips to diagnose and attack a spectrum of common search quality issues.
Recap of Activate 2018
We share our thoughts on the Lucidwork's Activate 2018 conference
Relevance Engineering is Here to Stay: Haystack EU 2018 Recap
I was privileged to participate in Haystack EU 2018 - relevance engineering as a discipline is here to stay, and just about every search & discovery team is scrambling to understand this new discipline.
Think AI will solve your search problems? Ask these questions first
This search stuff sounds like work - won't AI just solve all these problems soon?
event
Edui Conference - Leveraging Open Data for Deeper Insights
Explore key considerations for leveraging your existing data in conjunction with open third-party content in order to extract valuable insights through methods of analysis and visualization.
The Missing Hello World for OpenNLP
In 2012 I first saw OpenNLP, and was both excited by it, but also appalled by the documentation. I wrote this blog post in 2012, but turns out I never actually published it! So here it is, updated for OpenNLP 1.9.0!
training
Solr 'Think Like a Relevance Engineer' Training
Learn to improve search quality from the best experts in the field. From TFIDF, to Semantic Search, to Learning to Rank with Solr
Exploring Solr's OpenNLP Integrations
We share our thoughts on the Solr OpenNLP Integrations
training
Think Like a Relevance Engineer Training
Learn to improve search quality from the best experts in the field. From TFIDF, to Semantic Search, to Learning to Rank with Solr and Elasticsearch
Sub-phrase Highlighting in Solr
We share our attempts to implement partial phrase highlighting in Solr
Enterprise Data World 2018 Recap
Your precious data is typically an ugly unpolished gem. Enterprise Data World was all about how to polish it up! Some thoughts from a Relevancy perspective.
event
Berlin Buzzwords - The Neural Search Frontier
Will search relevance be revolutionized by deep learning? Join Doug Turnbull, author of 'Relevant Search', and Tommaso Teofili, author of 'Deep Learning for Search' as we explore the budding field of Neural Search.
Why We Created Search Relevance Training
I love Solr and Elasticsearch, BUT...
event
Cognitive Computing Summit - Learning To Rank
Learning to Rank (LTR) is now available for both Solr and Elasticsearch. Why is this such a hot topic? What does an organization need to leverage a Learning to Rank solution? Liz explains the LTR pipeline in terms of what is available as an off-the-shelf solution and what isn't. She discusses the challenges faced when implementing LTR and some open research areas moving forward.
Reflective Search Relevance Testing
Exploring a method of search relevance testing that doesnt suffer from drawbacks of clickstreams or expert user judgments
event
Haystack - The Search Relevance Conference.
Haystack is the conference for improving search relevance. Haystack is the no-holds-barred conference for organizations where search, matching, and relevance really matters to the bottom line.
How to Implement a Normalized Discounted Cumulative Gain (NDCG) Ranking Quality Scorer in Quepid
A guide on how to implement, test, and deploy a Normalized Discounted Cumulative Gain (NDCG) ranking quality scorer in Quepid.
event
Cognitive Solutions day
Want to hear how the next generation of digital solutions are applying AI and Machine Intelligence to create intelligent applications, like Chatbots and Virtual Assistants?
Solr Multiterm Synonyms: avoiding sow=false surprises
We document some of the behaviors behind Solr's relatively new sow=false strategy for parsing queries and dealing with query-time synonyms
Haystack Agenda Announced!
The agenda for Haystack - the search relevance talk - has been announced!
Elasticsearch Learning to Rank 1.0.1 Released
Elastic Cloud users rejoice! Elasticsearch LTR 1.0.1 released with support for XPack Security added.
Retaining Customers
Optimizing products to build real brand fanatics - beyond just 'conversions'.
Roll your own search analytics
Search metrics are crucial, and they're easy to do.
Why We're Doing a Search Relevance Conference
Why are we hosting this crazy Haystack conference? We want to bring together search relevance practitioners to discuss their hardest technical problems.
Solr Synonyms and Taxonomies: Mea Culpa
In my LuceneRevolution talk I neglected to discuss how SynonymQuery impacted index time semantic expansion. I discuss that oversight in detail here, with work arounds
event
Machinary.ai - Getting started with Learning To Rank
Overview, prerequisites, and implementation details of getting started with Learning To Rank. Why relevancy tuning will be taken over by machine learning, but not yet.
Vespa vs Lucene: First Impressions
Our first impressions of Vespa compared to Solr or Elasticsearch
Elasticsearch Learning to Rank 1.0 RC1 Released
We've released Elasticsearch Learning to Rank 1.0 RC1, which brings machine learning capabilities to Elasticsearch relevance ranking. Beginning the March to fully releasing version 1.0.
Solving The Search Management Minefield in Open Source Search
Don't be fooled by fancy technology: search is fundamentally a business problem; not a technical one. Technologists and domain experts need to establish careful contracts for managing search together.
How is search different than other machine learning problems?
In this article, I want to explore what makes search distinct from classic machine learning problems by giving you a tour of some different approaches.
Three Steps To Take Before Replacing Your Enterprise Search Solution
Replacing an enterprise search product? Use this three-step process to create actionable requirements for your team before you start.
Caching In Elasticsearch
What caching does Elasticsearch support, and what is the best way to take advantage of it?
We empower great search teams to achieve their potential
We teach some of the largest organizations how to deliver more accurate, relevant results with Solr and Elasticsearch. If search is core to your value, you should never outsource it.