Winning with Less for Low Resource Languages: Advantage of Cross-Lingual English_Persian Argument Mining Model over LLM Augmentation

TL;DR

This paper demonstrates that a lightweight cross-lingual argument mining model trained on English and Persian data outperforms LLM-augmented models, providing an effective solution for low-resource language argument mining.

Contribution

It introduces a cross-lingual training approach for argument mining that surpasses LLM augmentation methods in low-resource languages.

Findings

Cross-lingual model achieves 74.8% F1 on Persian argument mining.

LLM augmentation improves English F1 to 59.2%.

Zero-shot transfer yields around 50% F1 on both languages.

Abstract

Argument mining is a subfield of natural language processing to identify and extract the argument components, like premises and conclusions, within a text and to recognize the relations between them. It reveals the logical structure of texts to be used in tasks like knowledge extraction. This paper aims at utilizing a cross-lingual approach to argument mining for low-resource languages, by constructing three training scenarios. We examine the models on English, as a high-resource language, and Persian, as a low-resource language. To this end, we evaluate the models based on the English Microtext corpus \citep{PeldszusStede2015}, and its parallel Persian translation. The learning scenarios are as follow: (i) zero-shot transfer, where the model is trained solely with the English data, (ii) English-only training enhanced by synthetic examples generated by Large Language Models (LLMs), and (iii) a cross-lingual model that combines the original English data with manually translated Persian sentences. The zero-shot transfer model attains F1 scores of 50.2\% on the English test set and 50.7\% on the Persian test set. LLM-based augmentation model improves the performance up to 59.2\% on English and 69.3\% on Persian. The cross-lingual model, trained on both languages but evaluated solely on the Persian test set, surpasses the LLM-based variant, by achieving a F1 of 74.8\%. Results indicate that a lightweight cross-lingual blend can outperform considerably the more resource-intensive augmentation pipelines, and it offers a practical pathway for the argument mining task to overcome data resource shortage on low-resource languages.