Coarse-grained Argumentation Features for Scoring Persuasive Essays
Coarse-grained Argumentation Features for Scoring Persuasive Essays
复制标题
说服性论文评分的粗粒度论证特征
DOI：
10.18653/v1/p16-2089
复制
发表时间：
2016
期刊：
影响因子：
--
通讯作者：
S. Muresan
中科院分区：
文献类型：
--
作者：
Debanjan Ghosh;Aquila Khanam;Yubo Han;S. Muresan
对说服性文章的质量评分是语篇分析的一个重要目标，最近使用了与说服相关的高级特征，如论点清晰度，或观点及其目标。我们研究了从文章的粗粒度论辩结构中衍生出来的论辩特征是否有助于预测文章分数。我们引入了一组与论证成分(例如，主张和前提的数量)、论点关系(例如，支持的主张的数量)和论证结构的类型(链、树)相关的论证特征。我们发现，无论是人工标注还是自动预测粗糙的议论文结构，这些特征都能很好地预测托福论文的人类分数。
Scoring the quality of persuasive essays is an important goal of discourse analysis, addressed most recently with highlevel persuasion-related features such as thesis clarity, or opinions and their targets. We investigate whether argumentation features derived from a coarse-grained argumentative structure of essays can help predict essays scores. We introduce a set of argumentation features related to argument components (e.g., the number of claims and premises), argument relations (e.g., the number of supported claims) and typology of argumentative structure (chains, trees). We show that these features are good predictors of human scores for TOEFL essays, both when the coarsegrained argumentative structure is manually annotated and automatically predicted.