We rely on arguments in our daily lives to deliver our opinions and base them on evidence, making them more convincing in turn. However, finding and formulating arguments can be challenging. In this work, we train a language model for argument generation that can be controlled on a fine-grained level to generate sentence-level arguments for a given topic, stance, and aspect. We define argument aspect detection as a necessary method to allow this fine-granular control and crowdsource a dataset with 5,032 arguments annotated with aspects. Our evaluation shows that our generation model is able to generate high-quality, aspect-specific arguments. Moreover, these arguments can be used to improve the performance of stance detection models via data augmentation and to generate counter-arguments. We publish all datasets and code to fine-tune the language model.
Which Argumentative Aspects of Hate Speech in Social Media can be reliably identified?
Universidad de Buenos Aires(布宜诺斯艾利斯大学);Consejo Nacional de Investigaciones Científicas y Técnicas(阿根廷国家科学技术研究委员会);Universidad Nacional de Córdoba(科尔多瓦国立大学);Artificial Intelligence Research Institute (IIIA-CSIC)(人工智能研究所(IIIA-CSIC));Fundación Via Libre(自由之路基金会)
本文基于 Hateval 语料库和 Periodic Table of Arguments 标注仇恨言论的论证成分,评估各类论证特征的自动识别可靠性,并改进高错误类别。
A Controlled Synthetic Benchmark for Educational Aspect-Based Sentiment Analysis
Intelligent Systems, Afeka Academic College of Engineering(阿法卡学术工程智能系统学院);School of Computer Science, Faculty of Sciences, Holon Institute of Technology(霍洛技术学院计算机科学学院)
Universidade de São Paulo Center for Artificial Intelligence (C4AI)(圣保罗大学人工智能中心(C4AI));Instituto Mauá de Tecnologia Núcleo de Sistemas Eletrônicos Embarcados (NSEE)(马乌阿技术研究所电子系统嵌入核(NSEE))
Towards a Perspectivist Turn in Argument Quality Assessment
GESIS - Leibniz Institute for the Social Sciences(GESIS-莱布尼茨社会科学研究所);Leibniz University Hannover(汉诺威莱布尼茨大学);Heinrich-Heine University Düsseldorf(杜塞尔多夫海因里希·海涅大学)