RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación
Artículo científico (JournalArticle)
Transformer-Based Models for Automatic Identification of Argument Relations: A Cross-Domain Evaluation
[EN] Argument mining is defined as the task of automatically identifying and extracting argumentative components (e.g., premises, claims, etc.) and detecting the existing relations among them (i.e., support, attack, rephrase, no relation). One of the main issues when approaching this problem is the lack of data, and the size of the publicly available corpora. In this work, we use the recently annotated US2016 debate corpus. US2016 is the largest existing argument annotated corpus, which allows exploring the benefits of the most recent advances in natural language processing in a complex domain like argument (relation) mining. We present an exhaustive analysis of the behavior of transformer-based models (i.e., BERT, XLNET, RoBERTa, DistilBERT, and ALBERT) when predicting argument relations. Finally, we evaluate the models in five different domains, with the objective of finding the less domain-dependent model. We obtain a macro F1-score of 0.70 with the US2016 evaluation corpus, and a macro F1-score of 0.61 with the Moral Maze cross-domain corpus., This work was supported in part by the Spanish Government project under Grant TIN2017-89,156-R, in part by the FPI under grant BES-2015-074,498, and in part by the Valencian Government project under Grant PROMETEO/2018/002. The authors gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan V GPUs used for this research.
Proyecto:
Agencia Estatal de Investigación / Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016 TIN2017-89156-R
,
Generalitat Valenciana / Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020 PROMETEO/2018/002
,
Agencia Estatal de Investigación PID2020-113416RB-I00
,
Ministerio de Economía y Competitividad BES-2015-074498