TACLR: A Scalable and Efficient Retrieval-based Method for Industrial Product Attribute Value Identification

TL;DR

TACLR is a scalable retrieval-based method for product attribute value identification that effectively handles implicit, OOD, and normalized outputs, suitable for large-scale industrial deployment.

Contribution

It introduces a novel retrieval-based approach with taxonomy-aware contrastive learning for PAVI, addressing key limitations of existing methods.

Findings

Handles implicit and OOD values effectively

Scales to thousands of categories and millions of values

Successfully deployed in a real-world e-commerce platform

Abstract

Product Attribute Value Identification (PAVI) involves identifying attribute values from product profiles, a key task for improving product search, recommendation, and business analytics on e-commerce platforms. However, existing PAVI methods face critical challenges, such as inferring implicit values, handling out-of-distribution (OOD) values, and producing normalized outputs. To address these limitations, we introduce Taxonomy-Aware Contrastive Learning Retrieval (TACLR), the first retrieval-based method for PAVI. TACLR formulates PAVI as an information retrieval task by encoding product profiles and candidate values into embeddings and retrieving values based on their similarity. It leverages contrastive training with taxonomy-aware hard negative sampling and employs adaptive inference with dynamic thresholds. TACLR offers three key advantages: (1) it effectively handles implicit and OOD values while producing normalized outputs; (2) it scales to thousands of categories, tens of thousands of attributes, and millions of values; and (3) it supports efficient inference for high-load industrial deployment. Extensive experiments on proprietary and public datasets validate the effectiveness and efficiency of TACLR. Further, it has been successfully deployed on the real-world e-commerce platform Xianyu, processing millions of product listings daily with frequently updated, large-scale attribute taxonomies. We release the code to facilitate reproducibility and future research at https://github.com/SuYindu/TACLR.