Cluster Language Model for Improved E-Commerce Retrieval and Ranking: Leveraging Query Similarity and Fine-Tuning for Personalized Results

2023/09/25 by Don, Duleep Rathgamage, Xie, Ying, Yu, Le +2
#FOS: Computer and information sciences #I.2.7 #Information Retrieval (cs.IR)

paper · doi:10.48550/arxiv.2309.14323

Abstract

This paper proposes a novel method to improve the accuracy of product search in e-commerce by utilizing a cluster language model. The method aims to address the limitations of the bi-encoder architecture while maintaining a minimal additional training burden. The approach involves labeling top products for each query, generating semantically similar query clusters using the K-Means clustering algorithm, and fine-tuning a global language model into cluster language models on individual clusters. The parameters of each cluster language model are fine-tuned to learn local manifolds in the feature space efficiently, capturing the nuances of various query types within each cluster. The inference is performed by assigning a new query to its respective cluster and utilizing the corresponding cluster language model for retrieval. The proposed method results in more accurate and personalized retrieval results, offering a superior alternative to the popular bi-encoder based retrieval models in semantic search.

Related

• From Semantic Retrieval to Pairwise Ranking: Applying Deep Learning in E-commerce Search
• Context-Aware Clustering using Large Language Models
• Semantic Ads Retrieval at Walmart eCommerce with Language Models Progressively Trained on Multiple Knowledge Domains
• Generative Retrieval and Alignment Model: A New Paradigm for E-commerce Retrieval
• Cluster-based Adaptive Retrieval: Dynamic Context Selection for RAG Applications