arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1706.04033cs.AI
收藏

形式论证的自然语言生成

On Natural Language Generation of Formal Argumentation

Cardiff University(卡迪夫大学);University of St. Andrews(圣安德鲁斯大学);University of Southampton(南安普顿大学)

Federico Cerutti, Alice Toniolo, Timothy J. Norman

摘要:

在本文中,我们提供了一个第一次分析的研究问题时出现的问题,通过自然语言接口处理的问题,沟通件的正式论证。这是一个普遍持有的观点,论证的形式模型自然捕捉人类的论点,一些初步的研究集中在证明这一观点。不幸的是,结果不仅是不确定的,但似乎表明,向人类解释形式论证是一个相当明确的任务。用于表达基于论证的推理的图形模型很有吸引力,但人类通常需要大量的培训才能有效地使用这些工具。我们声称,自然语言接口正式论证系统提供了一个真正的替代方案,并可能是系统,捕捉人类的论点前进的方向。

英文摘要:

In this paper we provide a first analysis of the research questions that arise when dealing with the problem of communicating pieces of formal argumentation through natural language interfaces. It is a generally held opinion that formal models of argumentation naturally capture human argument, and some preliminary studies have focused on justifying this view. Unfortunately, the results are not only inconclusive, but seem to suggest that explaining formal argumentation to humans is a rather articulated task. Graphical models for expressing argumentation-based reasoning are appealing, but often humans require significant training to use these tools effectively. We claim that natural language interfaces to formal argumentation systems offer a real alternative, and may be the way forward for systems that capture human argument.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑