arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.00209cs.CL
收藏

高质量实时的结构化辩论生成

High Quality Real-Time Structured Debate Generation

Columbia University(哥伦比亚大学)

Eric Bolton, Alex Calderwood, Niles Christensen, Jerome Kafrouni, Iddo Drori

摘要:

自动生成辩论是一项具有挑战性的任务,需要理解论点以及如何否定或支持它们。在这项工作中,我们定义了辩论树和路径生成的辩论,同时执行一个高层次的结构和语法。我们利用了一个大型的树结构辩论语料库,每个论点都有元数据。我们开发了一个框架,用于生成似是而非的辩论是不可知的句子嵌入模型。我们的研究结果表明,有能力在实时的【形】产生辩论的复杂主题的质量,是接近人类,评估的风格,内容和战略指标用于判断竞争性的人类辩论。本着可重复研究的精神,我们将我们的数据、模型和代码公开提供。

英文摘要:

Automatically generating debates is a challenging task that requires an understanding of arguments and how to negate or support them. In this work we define debate trees and paths for generating debates while enforcing a high level structure and grammar. We leverage a large corpus of tree-structured debates that have metadata associated with each argument. We develop a framework for generating plausible debates which is agnostic to the sentence embedding model. Our results demonstrate the ability to generate debates in real-time on complex topics at a quality that is close to humans, as evaluated by the style, content, and strategy metrics used for judging competitive human debates. In the spirit of reproducible research we make our data, models, and code publicly available.

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。

↑