Octet: Online Catalog Taxonomy Enrichment with Self-Supervision

TL;DR

Octet is a self-supervised framework that effectively enriches online catalog taxonomies by leveraging heterogeneous online data and advanced neural models, doubling taxonomy size in real-world applications.

Contribution

The paper introduces a novel self-supervised end-to-end approach for taxonomy enrichment that requires no additional supervision and utilizes GNNs and sequence labeling for term extraction and attachment.

Findings

Octet outperforms state-of-the-art methods in automatic and human evaluations.

It doubles the size of an online catalog taxonomy in production.

The approach is effective across multiple online domains.

Abstract

Taxonomies have found wide applications in various domains, especially online for item categorization, browsing, and search. Despite the prevalent use of online catalog taxonomies, most of them in practice are maintained by humans, which is labor-intensive and difficult to scale. While taxonomy construction from scratch is considerably studied in the literature, how to effectively enrich existing incomplete taxonomies remains an open yet important research question. Taxonomy enrichment not only requires the robustness to deal with emerging terms but also the consistency between existing taxonomy structure and new term attachment. In this paper, we present a self-supervised end-to-end framework, Octet, for Online Catalog Taxonomy EnrichmenT. Octet leverages heterogeneous information unique to online catalog taxonomies such as user queries, items, and their relations to the taxonomy nodes while requiring no other supervision than the existing taxonomies. We propose to distantly train a sequence labeling model for term extraction and employ graph neural networks (GNNs) to capture the taxonomy structure as well as the query-item-taxonomy interactions for term attachment. Extensive experiments in different online domains demonstrate the superiority of Octet over state-of-the-art methods via both automatic and human evaluations. Notably, Octet enriches an online catalog taxonomy in production to 2 times larger in the open-world evaluation.