期刊
IEEE INTELLIGENT SYSTEMS
卷 36, 期 6, 页码 62-70出版社
IEEE COMPUTER SOC
DOI: 10.1109/MIS.2021.3073993
关键词
Task analysis; Ethics; Natural language processing; Data mining; Standards; Intelligent systems; Computational modeling
资金
- Spanish Government [TIN2017-89,156-R]
- FPI [BES-2015-074, 498]
- Valencian Government [PROMETEO/2018/002]
- NVIDIA Corporation
Argument mining involves automatically identifying and extracting argumentative components and detecting the relations among them. This study utilized the US2016 debate corpus to analyze the performance of transformer-based models in predicting argument relations and aimed to find a model that is less dependent on specific domains. The research achieved a macro F1-score of 0.70 with the US2016 corpus and 0.61 with the Moral Maze cross-domain corpus.
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据