Cross-lingual Argument Mining in the Medical Domain

TL;DR

This paper explores cross-lingual argument mining in the medical domain, demonstrating that data transfer via translation outperforms multilingual models and can enhance English argument mining through data augmentation.

Contribution

It introduces an effective data-transfer approach for argument mining in low-resource languages and shows its superiority over model-transfer methods in medical texts.

Findings

Data-transfer outperforms model-transfer in cross-lingual argument mining.

Automatically translated data improves English argument mining performance.

Proposed method enables automatic data augmentation for low-resource languages.

Abstract

Nowadays the medical domain is receiving more and more attention in applications involving Artificial Intelligence as clinicians decision-making is increasingly dependent on dealing with enormous amounts of unstructured textual data. In this context, Argument Mining (AM) helps to meaningfully structure textual data by identifying the argumentative components in the text and classifying the relations between them. However, as it is the case for man tasks in Natural Language Processing in general and in medical text processing in particular, the large majority of the work on computational argumentation has been focusing only on the English language. In this paper, we investigate several strategies to perform AM in medical texts for a language such as Spanish, for which no annotated data is available. Our work shows that automatically translating and projecting annotations (data-transfer) from English to a given target language is an effective way to generate annotated data without costly manual intervention. Furthermore, and contrary to conclusions from previous work for other sequence labelling tasks, our experiments demonstrate that data-transfer outperforms methods based on the crosslingual transfer capabilities of multilingual pre-trained language models (model-transfer). Finally, we show how the automatically generated data in Spanish can also be used to improve results in the original English monolingual setting, providing thus a fully automatic data augmentation strategy.