Active Learning for Product Type Ontology Enhancement in E-commerce

TL;DR

This paper presents an active learning framework that leverages domain experts to efficiently enhance product type ontologies in e-commerce, improving search accuracy with less manual effort.

Contribution

It introduces a novel active learning approach tailored for product type ontology construction in e-commerce, reducing human effort while maintaining quality.

Findings

The framework effectively improves product type coverage.

It achieves high-quality ontology with less expert involvement.

Experimental results demonstrate enhanced search relevance.

Abstract

Entity-based semantic search has been widely adopted in modern search engines to improve search accuracy by understanding users' intent. In e-commerce, an accurate and complete product type (PT) ontology is essential for recognizing product entities in queries and retrieving relevant products from catalog. However, finding product types (PTs) to construct such an ontology is usually expensive due to the considerable amount of human efforts it may involve. In this work, we propose an active learning framework that efficiently utilizes domain experts' knowledge for PT discovery. We also show the quality and coverage of the resulting PTs in the experiment results.