End-to-end Argument Mining with Cross-corpora Multi-task Learning

• Published in: Transactions of the Association for Computational Linguistics Vol. 10; pp. 639 - 658
• Main Authors: Morio, Gaku, Ozaki, Hiroaki, Morishita, Terufumi, Yanai, Kohsuke
• Format: Journal Article
• Language: English
• Published: One Broadway, 12th Floor, Cambridge, Massachusetts 02142, USA MIT Press 16.05.2022; MIT Press Journals, The; The MIT Press
• Subjects: Annotations; Argument structure; Automatic summarization; Classification; Corpus analysis; Linguistics; Neural networks; Training
• ISSN: 2307-387X; 2307-387X
• DOI: 10.1162/tacl_a_00481

Mining an argument structure from text is an important step for tasks such as argument search and summarization. While studies on argument(ation) mining have proposed promising neural network models, they usually suffer from a shortage of training data. To address this issue, we expand the training data with various auxiliary argument mining corpora and propose an end-to-end cross-corpus training method called ( ). To evaluate our approach, we conducted experiments for the main argument mining tasks on several well-established argument mining corpora. The results demonstrate that MT-AM generally outperformed the models trained on a single corpus. Also, the smaller the target corpus was, the better the MT-AM performed. Our extensive analyses suggest that the improvement of MT-AM depends on several factors of transferability among auxiliary and target corpora.