ReCAP-II: Information Retrieval and Case-Based Reasoning for Robust Deliberation and Synthesisof Arguments – Architecture and Applications

ReCAP提案遵循了未来论证机器的愿景，支持研究人员，新闻作家以及人类决策者获得与某个主题相关的当前论证和观点的全面概述，以及通过令人信服的论证来发展个人的，有充分根据的观点。这种论证机器自动探索和处理网络上可用的信息源，特别是与讨论的特定主题相关的论证文本和事实内容。与现有搜索引擎主要在文本层面操作不同，这种论证机将在由论证和论证结构形成的知识层面进行推理。在给定的特定语境下，这种推理将积极地支持对正在考虑的问题的论证和反论证的审议，基于网络上现有的观点和事实。此外，它将支持对审议过程的新贡献的综合，基于类似相关背景和主题的论点和论点结构的类比转移。ReCAP项目旨在通过一个与优先计划比率中的其他项目相关联的研究计划，为实现这一愿景做出重大贡献。重点是对信息检索（IR）和知识表示与推理（RI）方法的新贡献和融合，特别是基于案例的推理。其目的是开发能够以健壮和可扩展的方式捕获参数的方法，特别是表示、上下文化和聚合参数并使其可供用户使用。为了全面了解已经处于项目早期阶段的论证机的潜在未来用途，并将重点放在方法学和实验研究工作上，我们纳入了政治辩论专家的应用伙伴。我们将开发专业注释的语料库，并制定若干用例供审议和综合，作为金标准，这些用例也将与优先计划中的其他项目共享，以达到基准目的。

The ReCAP proposal follows the vision of future argumentation machines that support researchers, journalistic writers, as well as human decision makers to obtain a comprehensive overview of current arguments and opinions related to a certain topic, as well as to develop personal, well-founded opinions justified by convincing arguments. Such argumentation machines automatically explore and process available information sources on the web, particularly argumentative texts and factual content relevant for the specific topic under discussion. Unlike existing search engines, which primarily operate on the textual level, such argumentation machines will reason on a knowledge level formed by arguments and argumentation structures. For a given particular context, such reasoning will actively support the deliberation of arguments and counter-arguments for the issue under consideration, based on present opinions and facts on the Web. In addition, it will support the synthesis of new contributions to the deliberation process, based on analogical transfer of arguments and argumentation structures from similar related contexts and topics.The ReCAP project aims at significantly contributing to the realisation of this vision by a research program, linked with the other projects in the Priority Programme RATIO. The focus is on the novel contributions to and confluence of methods from information retrieval (IR) and knowledge representation and reasoning (RI), in particular case-based reasoning. The aim is to develop methods that are able to capture arguments in a robust and scalable manner, in particular representing, contextualizing, and aggregating arguments and making them available to a user. To develop a comprehensive understanding of the potential future uses of argumentation machines already in the early phase of the project and to focus the methodological and experimental research work we include application partners who are experts in political debates. We will develop professionally annotated corpora and elaborate several use cases for deliberation and synthesis as gold standard, which will also be shared with the other projects in the Priority Programme for benchmarking purposes.