Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Improving Product Search Relevance with EAR-MP: A Solution for the CIKM 2025 AnalytiCup

JaeEun Lim, Soomin Kim, Jaeyong Seo, Iori Ono, Qimu Ran, Jae-woong Lee

TL;DR

This paper documents the solution employed by the EAR-MP team for the CIKM 2025 AnalytiCup, which addresses two core tasks: Query-Category (QC) relevance and Query-Item (QI) relevance, and first normalizes the multilingual dataset by translating all text into English, then mitigates noise through extensive data cleaning and normalization.

Abstract

Multilingual e-commerce search is challenging due to linguistic diversity and the noise inherent in user-generated queries. This paper documents the solution employed by our team (EAR-MP) for the CIKM 2025 AnalytiCup, which addresses two core tasks: Query-Category (QC) relevance and Query-Item (QI) relevance. Our approach first normalizes the multilingual dataset by translating all text into English, then mitigates noise through extensive data cleaning and normalization. For model training, we build on DeBERTa-v3-large and improve performance with label smoothing, self-distillation, and dropout. In addition, we introduce task-specific upgrades, including hierarchical token injection for QC and a hybrid scoring mechanism for QI. Under constrained compute, our method achieves competitive results, attaining an F1 score of 0.8796 on QC and 0.8744 on QI. These findings underscore the importance of systematic data preprocessing and tailored training strategies for building robust, resource-efficient multilingual relevance systems.

Improving Product Search Relevance with EAR-MP: A Solution for the CIKM 2025 AnalytiCup

TL;DR

This paper documents the solution employed by the EAR-MP team for the CIKM 2025 AnalytiCup, which addresses two core tasks: Query-Category (QC) relevance and Query-Item (QI) relevance, and first normalizes the multilingual dataset by translating all text into English, then mitigates noise through extensive data cleaning and normalization.

Abstract

Multilingual e-commerce search is challenging due to linguistic diversity and the noise inherent in user-generated queries. This paper documents the solution employed by our team (EAR-MP) for the CIKM 2025 AnalytiCup, which addresses two core tasks: Query-Category (QC) relevance and Query-Item (QI) relevance. Our approach first normalizes the multilingual dataset by translating all text into English, then mitigates noise through extensive data cleaning and normalization. For model training, we build on DeBERTa-v3-large and improve performance with label smoothing, self-distillation, and dropout. In addition, we introduce task-specific upgrades, including hierarchical token injection for QC and a hybrid scoring mechanism for QI. Under constrained compute, our method achieves competitive results, attaining an F1 score of 0.8796 on QC and 0.8744 on QI. These findings underscore the importance of systematic data preprocessing and tailored training strategies for building robust, resource-efficient multilingual relevance systems.
Paper Structure (23 sections, 3 equations, 1 figure, 6 tables)

This paper contains 23 sections, 3 equations, 1 figure, 6 tables.

Table of Contents

  1. Introduction
  2. Background
  3. Dataset and Problem
  4. METHODOLOGY
  5. Overall Architecture
  6. Data Preprocessing
  7. Translate to English
  8. Data Cleaning and Normalization
  9. Model
  10. Label Smoothing
  11. QC Task Strategies
  12. Hierarchical Token Injection for Category Paths
  13. Leaf Category Threshold Tuning
  14. Dropout Strategy
  15. QI Task Strategies
  16. ...and 8 more sections

Figures (1)

  • Figure 1: Overall pipeline for multilingual product search: preprocessing (translate to English, cleaning/normalization) → DeBERTa-v3-large training (label smoothing) → task-specific upgrades (QC/QI).