Harnessing rhetorical figures for argument mining
Harnessing rhetorical figures for argument mining
复制标题
利用修辞手法进行论点挖掘
DOI：
--
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
C. Reed
中科院分区：
文献类型：
--
作者：
John Lawrence;J. Visser;C. Reed
。对说服性沟通背后的推理结构进行一般化、自动化的重建是一项极具挑战性的任务。虽然论证挖掘的这项工作越来越多地受到计算fi领域以外的论证研究的丰富传统的启发，但到目前为止，对论证的修辞角度在很大程度上被忽视了。为了探索修辞洞察力在论证挖掘中的应用，我们对修辞fi准则与论证结构之间的关系进行了初步研究。修辞fi是一种在论辩语篇中发挥多种功能的语言手段。其中一些fiGUE的文本形式很容易自动识别，因此在fiGUE和大多数论点内容之间建立的连接将提高论点挖掘技术的性能。此外，修辞类fi词的自动挖掘可以作为基于语料库的经验性测试平台，来检验修辞学文献中关于这些fi类词的说法。在初步研究中，我们探索了八种修辞fi图形与论证结构之间的联系，我们期望这些图形的形式在计算上相对容易识别，并将它们的出现与推理关系和fl信息通信技术联系起来(具体地说，我们认为这六种修辞图形的出现与推理和推理的关系有关)。这项研究的数据来自MM2012c语料库，该语料库包含39,694字的议论文注释文本，来自英国广播公司广播四台的S道德迷宫讨论节目。我们表明，相对于整个文本，fi的一些GUE确实对应于论证密度较高的段落。
. The generalised, automated reconstruction of the reasoning structures underlying persuasive communication is an enormously challenging task. While this work in argument mining is increasingly informed by the rich tradition of argumentation studies outside the computational field, the rhetorical perspective on argumentation is thus far largely ignored. To explore the application of rhetorical insights in argument mining, we conduct a pilot study on the connection between rhetorical figures and argumentation structure. Rhetorical figures are linguistic devices that perform a variety of functions in argumentative discourse. The textual form of some of these figures is easy to identify automatically, such that an established connection between the figure and a preponderance of argumentative content would improve the performance of argument mining techniques. Furthermore, the automated mining of rhetorical figures could be used as an empirical, corpus-based testing ground for the claims made about these figures in the rhetorical literature. In the pilot study, we explore the connection between eight rhetorical fig-ures the forms of which we expect to be relatively easy to identify computationally, and argumentation structure (concretely, we consider the six schemes ‘anadiplosis’, ‘epanaphora’, ‘epistrophe’, ‘epizeuxis’, ‘eutrepismus’, and ‘polyptoton’, and the two tropes ‘antithesis’ and ‘dirimens copulatio’, and relate their occurrences to relations of inference and conflict). The data of the study is collected in the MM2012c corpus of 39,694 words of argumentatively annotated transcripts from the BBC Radio 4’s Moral Maze discussion program. We show that some of the figures indeed correspond to passages of high argumentative density, relative to the text as a whole.