CAT-ID$^2$: Category-Tree Integrated Document Identifier Learning for Generative Retrieval In E-commerce

TL;DR

This paper introduces CAT-ID$^2$, a novel method for generating document identifiers in e-commerce that incorporate category information, improving retrieval accuracy and user engagement in generative retrieval systems.

Contribution

The paper proposes a new ID learning approach that integrates category-tree information into semantic IDs, enhancing representational power and retrieval performance.

Findings

Improved document ID quality with category integration.

Enhanced retrieval accuracy demonstrated by online A/B tests.

Increased user engagement metrics in e-commerce search.

Abstract

Generative retrieval (GR) has gained significant attention as an effective paradigm that integrates the capabilities of large language models (LLMs). It generally consists of two stages: constructing discrete semantic identifiers (IDs) for documents and retrieving documents by autoregressively generating ID tokens. The core challenge in GR is how to construct document IDs (DocIDS) with strong representational power. Good IDs should exhibit two key properties: similar documents should have more similar IDs, and each document should maintain a distinct and unique ID. However, most existing methods ignore native category information, which is common and critical in E-commerce. Therefore, we propose a novel ID learning method, CAtegory-Tree Integrated Document IDentifier (CAT-ID$^2$), incorporating prior category information into the semantic IDs. CAT-ID$^2$ includes three key modules: a Hierarchical Class Constraint Loss to integrate category information layer by layer during quantization, a Cluster Scale Constraint Loss for uniform ID token distribution, and a Dispersion Loss to improve the distinction of reconstructed documents. These components enable CAT-ID$^2$ to generate IDs that make similar documents more alike while preserving the uniqueness of different documents' representations. Extensive offline and online experiments confirm the effectiveness of our method, with online A/B tests showing a 0.33% increase in average orders per thousand users for ambiguous intent queries and 0.24% for long-tail queries.