Back to ECNLP 2024
LREC-COLING 2024workshop

Don’t Just Translate, Summarize Too: Cross-lingual Product Title Generation in E-commerce

Proceedings of the Seventh Workshop on e-Commerce and NLP @ LREC-COLING 2024

DOI:10.63317/55eis6dq5efe

Abstract

Making product titles informative and concise is vital to delighting e-commerce customers. Recent advances have successfully applied monolingual product title summarization to shorten lengthy product titles. This paper explores the cross-lingual product title generation task that summarizes and translates the source language product title to a shortened product title in the target language. Our main contributions are as follows, (i) we investigate the optimal product title length within the scope of e-commerce localization, (ii) we introduce a simple yet effective data filtering technique to train a length-aware machine translation system and compare it to a publicly available LLM, (iii) we propose an automatic approach to validate experimental results using an open-source LLM without human input and show that these evaluation results are consistent with human preferences.

Details

Paper ID
lrec2024-ws-ecnlp-06
Pages
pp. 58-64
BibKey
zhang-etal-2024-dont
Editor
N/A
Publisher
European Language Resources Association (ELRA) and ICCL
ISSN
N/A
ISBN
N/A
Workshop
Proceedings of the Seventh Workshop on e-Commerce and NLP @ LREC-COLING 2024
Location
undefined, undefined
Date
20 May 2024 25 May 2024

Authors

  • BZ

    Bryan Zhang

  • TN

    Taichi Nakatani

  • DH

    Daniel Vidal Hussey

  • SW

    Stephan Walter

  • LT

    Liling Tan

Links