Saved in:
Bibliographic Details
Main Authors: Lim, JaeEun, Kim, Soomin, Seo, Jaeyong, Ono, Iori, Ran, Qimu, Lee, Jae-woong
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.23018
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908622127104000
author Lim, JaeEun
Kim, Soomin
Seo, Jaeyong
Ono, Iori
Ran, Qimu
Lee, Jae-woong
author_facet Lim, JaeEun
Kim, Soomin
Seo, Jaeyong
Ono, Iori
Ran, Qimu
Lee, Jae-woong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_23018
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Improving Product Search Relevance with EAR-MP: A Solution for the CIKM 2025 AnalytiCup
Lim, JaeEun
Kim, Soomin
Seo, Jaeyong
Ono, Iori
Ran, Qimu
Lee, Jae-woong
Information Retrieval
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.
title Improving Product Search Relevance with EAR-MP: A Solution for the CIKM 2025 AnalytiCup
topic Information Retrieval
url https://arxiv.org/abs/2510.23018