Enhancing E-commerce Product Title Translation with Retrieval-Augmented Generation and Large Language Models

TL;DR

This paper introduces a retrieval-augmented generation method that improves multilingual e-commerce product title translation by leveraging bilingual data, significantly enhancing translation quality especially for less proficient language pairs.

Contribution

The study presents a novel RAG approach that incorporates bilingual product examples as prompts to boost LLM translation performance in e-commerce contexts.

Findings

Up to 15.3% chrF score improvement for low-proficiency language pairs

Effective use of bilingual retrieval to enhance translation accuracy

Demonstrates the benefit of retrieval-augmented methods in specialized translation tasks.

Abstract

E-commerce stores enable multilingual product discovery which require accurate product title translation. Multilingual large language models (LLMs) have shown promising capacity to perform machine translation tasks, and it can also enhance and translate product titles cross-lingually in one step. However, product title translation often requires more than just language conversion because titles are short, lack context, and contain specialized terminology. This study proposes a retrieval-augmented generation (RAG) approach that leverages existing bilingual product information in e-commerce by retrieving similar bilingual examples and incorporating them as few-shot prompts to enhance LLM-based product title translation. Experiment results show that our proposed RAG approach improve product title translation quality with chrF score gains of up to 15.3% for language pairs where the LLM has limited proficiency.