Taxonomic Search – A Powerful Lever for Boosting Relevance and Understanding Query Intent

Posted: 16 Dec 2019

Date Written: December 16, 2019

Abstract

A carefully built, well applied and intuitively surfaced taxonomy can really help us reach the holy grail of search, namely increased recall and precision in results. This work looks at how we construct taxonomies at LexisNexis that match content volume and customer need to provide topics that are granular enough to be actionable, insightful and helpful in decision-making. It covers both rule-based and machine learning classification approaches to content enrichment and demonstrates how we combine these to achieve compelling and differentiating accuracy. It looks at the various ways we have surfaced taxonomy in our products both to enable our customers to get to the comprehensive information they want faster and increasingly to drive powerful analytics. Finally, we look to the future and consider how we can increase usage of our taxonomies both explicitly and ‘hands-free’ in our products to continue to boost relevance, improve findability and better understand query intent.

Keywords: taxonomy, search relevance, query intent, ontology, facets, content enrichment, machine-learning, rules-based classification, query matching

Suggested Citation

Fea, Mark and Warling, Robin and Lagace, Sophie and Piggott, James, Taxonomic Search – A Powerful Lever for Boosting Relevance and Understanding Query Intent (December 16, 2019). Proceedings of the 3rd Annual RELX Search Summit, Available at SSRN: https://ssrn.com/abstract=3504576

Mark Fea (Contact Author)

LexisNexis ( email )

P. O. Box 933
Dayton, OH 45401
United States

Robin Warling

LexisNexis ( email )

P. O. Box 933
Dayton, OH 45401
United States

Sophie Lagace

LexisNexis ( email )

P. O. Box 933
Dayton, OH 45401
United States

James Piggott

LexisNexis ( email )

P. O. Box 933
Dayton, OH 45401
United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Abstract Views
146
PlumX Metrics