Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Data-Centric Approach to Multilingual E-Commerce Product Search: Case Study on Query-Category and Query-Item Relevance

Yabo Yin, Yang Xi, Jialong Wang, Shanqi Wang, Jiateng Hu

TL;DR

This work presents a practical, architecture-agnostic, data-centric framework to enhance performance on two core tasks: Query-Category (QC) relevance and Query-Item (QI) relevance, offering actionable guidance for building robust multilingual search systems in the real-world e-commerce settings.

Abstract

Multilingual e-commerce search suffers from severe data imbalance across languages, label noise, and limited supervision for low-resource languages--challenges that impede the cross-lingual generalization of relevance models despite the strong capabilities of large language models (LLMs). In this work, we present a practical, architecture-agnostic, data-centric framework to enhance performance on two core tasks: Query-Category (QC) relevance (matching queries to product categories) and Query-Item (QI) relevance (matching queries to product titles). Rather than altering the model, we redesign the training data through three complementary strategies: (1) translation-based augmentation to synthesize examples for languages absent in training, (2) semantic negative sampling to generate hard negatives and mitigate class imbalance, and (3) self-validation filtering to detect and remove likely mislabeled instances. Evaluated on the CIKM AnalytiCup 2025 dataset, our approach consistently yields substantial F1 score improvements over strong LLM baselines, achieving competitive results in the official competition. Our findings demonstrate that systematic data engineering can be as impactful as--and often more deployable than--complex model modifications, offering actionable guidance for building robust multilingual search systems in the real-world e-commerce settings.

A Data-Centric Approach to Multilingual E-Commerce Product Search: Case Study on Query-Category and Query-Item Relevance

TL;DR

This work presents a practical, architecture-agnostic, data-centric framework to enhance performance on two core tasks: Query-Category (QC) relevance and Query-Item (QI) relevance, offering actionable guidance for building robust multilingual search systems in the real-world e-commerce settings.

Abstract

Multilingual e-commerce search suffers from severe data imbalance across languages, label noise, and limited supervision for low-resource languages--challenges that impede the cross-lingual generalization of relevance models despite the strong capabilities of large language models (LLMs). In this work, we present a practical, architecture-agnostic, data-centric framework to enhance performance on two core tasks: Query-Category (QC) relevance (matching queries to product categories) and Query-Item (QI) relevance (matching queries to product titles). Rather than altering the model, we redesign the training data through three complementary strategies: (1) translation-based augmentation to synthesize examples for languages absent in training, (2) semantic negative sampling to generate hard negatives and mitigate class imbalance, and (3) self-validation filtering to detect and remove likely mislabeled instances. Evaluated on the CIKM AnalytiCup 2025 dataset, our approach consistently yields substantial F1 score improvements over strong LLM baselines, achieving competitive results in the official competition. Our findings demonstrate that systematic data engineering can be as impactful as--and often more deployable than--complex model modifications, offering actionable guidance for building robust multilingual search systems in the real-world e-commerce settings.
Paper Structure (20 sections, 5 equations, 2 figures, 3 tables)

This paper contains 20 sections, 5 equations, 2 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Method
  4. Base Model and Task Formulation
  5. Data-Centric Enhancement Strategies
  6. Translation-Based Data Augmentation for Language Generalization
  7. Semantic Negative Sampling for Class Imbalance
  8. Self-Validation Filtering for Noisy Labels
  9. Model Training and Inference
  10. Model Training
  11. Model Inference
  12. Experiments
  13. Experimental Settings
  14. Datasets
  15. Implementation Details
  16. ...and 5 more sections

Figures (2)

  • Figure 1: Overview of the proposed data-centric framework for the Query-Category (QC) relevance task.
  • Figure 2: Performance comparison of QC and QI tasks across different prediction thresholds.