{"ID":2837204,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.20872","arxiv_id":"2511.20872","title":"Winning with Less for Low Resource Languages: Advantage of Cross-Lingual English_Persian Argument Mining Model over LLM Augmentation","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.","short_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...","url_abs":"https://arxiv.org/abs/2511.20872","url_pdf":"https://arxiv.org/pdf/2511.20872v1","authors":"[\"Ali Jahan\",\"Masood Ghayoomi\",\"Annette Hautli-Janisz\"]","published":"2025-11-25T21:36:39Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}