Leveraging Catalog Knowledge Graphs for Query Attribute Identification in E-Commerce Sites

TL;DR

This paper introduces a framework that uses catalog-derived knowledge graphs to resolve conflicting attributes in e-commerce queries, improving attribute identification and search relevance.

Contribution

It presents a novel approach leveraging catalog knowledge graphs to address attribute conflicts in e-commerce queries, enhancing search accuracy.

Findings

Resolving attribute conflicts improves search relevance.

Catalog knowledge graphs outperform traditional methods.

Framework effective on real-world e-commerce queries.

Abstract

Millions of people use online e-commerce platforms to search and buy products. Identifying attributes in a query is a critical component in connecting users to relevant items. However, in many cases, the queries have multiple attributes, and some of them will be in conflict with each other. For example, the query "maroon 5 dvds" has two candidate attributes, the color "maroon" or the band "maroon 5", where only one of the attributes can be present. In this paper, we address the problem of resolving conflicting attributes in e-commerce queries. A challenge in this problem is that knowledge bases like Wikipedia that are used to understand web queries are not focused on the e-commerce domain. E-commerce search engines, however, have access to the catalog which contains detailed information about the items and its attributes. We propose a framework that constructs knowledge graphs from catalog to resolve conflicting attributes in e-commerce queries. Our experiments on real-world queries on e-commerce platforms demonstrate that resolving conflicting attributes by leveraging catalog information significantly improves attribute identification, and also gives out more relevant search results.