Multilingual Argument Mining: Datasets and Analysis

TL;DR

This paper investigates multilingual argument mining using transfer learning with multilingual BERT, analyzing how translation-based methods perform across languages and providing new multilingual datasets for evaluation.

Contribution

It introduces a multilingual argument mining approach leveraging transfer learning and provides a new multilingual dataset for benchmarking.

Findings

Transfer learning works well for stance classification and evidence detection.

Quality assessment of arguments is less effective with translation-based methods.

Language choice and relations impact translation-based model accuracy.

Abstract

The growing interest in argument mining and computational argumentation brings with it a plethora of Natural Language Understanding (NLU) tasks and corresponding datasets. However, as with many other NLU tasks, the dominant language is English, with resources in other languages being few and far between. In this work, we explore the potential of transfer learning using the multilingual BERT model to address argument mining tasks in non-English languages, based on English datasets and the use of machine translation. We show that such methods are well suited for classifying the stance of arguments and detecting evidence, but less so for assessing the quality of arguments, presumably because quality is harder to preserve under translation. In addition, focusing on the translate-train approach, we show how the choice of languages for translation, and the relations among them, affect the accuracy of the resultant model. Finally, to facilitate evaluation of transfer learning on argument mining tasks, we provide a human-generated dataset with more than 10k arguments in multiple languages, as well as machine translation of the English datasets.