GSID: Generative Semantic Indexing for E-Commerce Product Understanding

2025/09/28 by Yang, Haiyang, Xie, Qinye, Zhang, Qingheng +7 · 1 citation
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Information Retrieval (cs.IR)

paper · doi:10.48550/arxiv.2509.23860

Abstract

Structured representation of product information is a major bottleneck for the efficiency of e-commerce platforms, especially in second-hand ecommerce platforms. Currently, most product information are organized based on manually curated product categories and attributes, which often fail to adequately cover long-tail products and do not align well with buyer preference. To address these problems, we propose Generative Semantic InDexings (GSID), a data-driven approach to generate product structured representations. GSID consists of two key components: (1) Pre-training on unstructured product metadata to learn in-domain semantic embeddings, and (2) Generating more effective semantic codes tailored for downstream product-centric applications. Extensive experiments are conducted to validate the effectiveness of GSID, and it has been successfully deployed on the real-world e-commerce platform, achieving promising results on product understanding and other downstream tasks.

Citations

• TACLR: A Scalable and Efficient Retrieval-based Method for Industrial Product Attribute Value Identification
• MetaSplit: Meta-Split Network for Limited-Stock Product Recommendation
• C-Pack: Packed Resources For General Chinese Embeddings
• Towards Open-World Product Attribute Mining: A Lightly-Supervised Approach
• Learning to Tokenize for Generative Retrieval
• Autoregressive Image Generation using Residual Quantization
• Transformer Memory as a Differentiable Search Index
• Mengzi: Towards Lightweight yet Ingenious Pre-trained Models for Chinese
• Deep Hierarchical Classification for Category Prediction in E-commerce System
• AliCoCo: Alibaba E-commerce Cognitive Concept Net
• Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
• Neural Discrete Representation Learning
• Deep Interest Network for Click-Through Rate Prediction
• Sequence to Sequence Learning with Neural Networks

Cited by

• LLP: LLM-based Product Pricing in E-commerce

Related

• Semantic Product Search for Matching Structured Product Catalogs in E-Commerce
• Generative Retrieval and Alignment Model: A New Paradigm for E-commerce Retrieval
• Query2Prod2Vec Grounded Word Embeddings for eCommerce
• Learning-To-Embed: Adopting Transformer based models for E-commerce Products Representation Learning
• Product Classification in E-Commerce using Distributional Semantics