Utilize Transformers for translating Wikipedia category names

TL;DR

This paper presents a Transformer-based approach for translating Wikipedia category names from English to Vietnamese, demonstrating effective performance with resource-efficient models and a specialized dataset.

Contribution

It introduces a dataset of 15,000 English-Vietnamese category pairs and fine-tunes Transformer models for category translation, highlighting OPUS-MT-en-vi's superior BLEU score.

Findings

OPUS-MT-en-vi achieved a BLEU score of 0.73

Transformer models outperformed baseline methods

Resource-efficient models can effectively translate Wikipedia categories

Abstract

On Wikipedia, articles are categorized to aid readers in navigating content efficiently. The manual creation of new categories can be laborious and time-intensive. To tackle this issue, we built language models to translate Wikipedia categories from English to Vietnamese with a dataset containing 15,000 English-Vietnamese category pairs. Subsequently, small to medium-scale Transformer pre-trained models with a sequence-to-sequence architecture were fine-tuned for category translation. The experiments revealed that OPUS-MT-en-vi surpassed other models, attaining the highest performance with a BLEU score of 0.73, despite its smaller model storage. We expect our paper to be an alternative solution for translation tasks with limited computer resources.