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

2025-01-07

AI Summary

Existing Product Attribute Value Identification (PAVI) methods face significant bottlenecks in implicit attribute mining, out-of-distribution (OOD) value detection, and output standardization, rendering them inadequate for large-scale, multi-category, multi-attribute, and multi-value industrial e-commerce applications. This paper proposes the first retrieval-based modeling paradigm for PAVI, featuring a category-aware contrastive learning dual-tower architecture. We introduce category-guided hard negative sampling and a dynamic similarity thresholding inference mechanism to jointly address implicit value recall, robust OOD value identification, and normalized output generation. The framework scales to thousands of categories, tens of thousands of attributes, and millions of candidate values. Deployed industrially, it processes one million products daily. Extensive experiments demonstrate substantial improvements over state-of-the-art methods in both accuracy and throughput.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Computer Vision: Image and Video Retrieval
• Machine Learning: Learning Preferences or Rankings

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Product Attribute Value Identification (PAVI) involves identifying attribute values from product profiles, a key task for improving product search, recommendations, 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 to the item embedding. 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 scenarios. Extensive experiments on proprietary and public datasets validate the effectiveness and efficiency of TACLR. Moreover, it has been successfully deployed in a real-world e-commerce platform, processing millions of product listings daily while supporting dynamic, large-scale attribute taxonomies.

Problem

• Product Attribute Value Identification
• Implicit Attributes
• Normalization Output

Innovation

• TACLR
• Retrieval-based PAVI
• Classification Contrastive Learning