Artificial Intelligence and Law studies how legal reasoning can be formalized in order to eventually be able to develop systems that assist lawyers in the task of researching, drafting and evaluating arguments in a professional setting. To further this goal, researchers have been developing systems, which, to a limited extent, autonomously engage in legal reasoning, and argumentation on closed domains. This dissertation presents the Value Judgment Formalism and its experimental implementation in the VJAP system, which is capable of arguing about, and predicting outcomes of, a set of trade secret misappropriation cases.ududVJAP argues about cases by creating an argument graph for each case using a set of argument schemes. These schemes use a representation of values underlying trade secret law and effects of facts on these values. VJAP argumentatively balances effects in the given case and analogizes it to individual precedents and the value tradeoffs in those precedents. It predicts case outcomes using a confidence measure computed from the argument graph and generates textual legal arguments justifying its predictions. The confidence propagation uses quantitative weights assigned to effects of facts on values. VJAP automatically learns these weights from past cases using an iterative optimization method.ududThe experimental evaluation shows that VJAP generates case-based legal arguments that make plausible and intelligent-appearing use of precedents to reason about a case in terms of differences and similarities to a precedent and the value tradeoffs that both contain. VJAP’s prediction performance is promising when compared to machine learning algorithms, which do not generate legal arguments. Due to the small case base, however, the assessment of prediction performance was not statistically rigorous. VJAP exhibits argumentation and prediction behavior that, to some extent, resembles phenomena in real case-based legal reasoning, such as realistically appearing citation graphs.ududThe VJAP system and experiment demonstrate that it is possible to effectively combine symbolic knowledge and inference with quantitative confidence propagation. In AI&Law, such systems can embrace the structure of legal reasoning and learn quantitative information about the domain from prior cases, as well as apply this information in a structurally realistic way in the context of new cases.
展开▼
机译：人工智能和法律学院研究如何将法律推理形式化，以便最终能够开发出可协助律师在专业环境中研究，起草和评估论点的系统。为了实现这一目标，研究人员一直在开发系统，该系统在有限的范围内自主从事法律推理和对封闭域的争论。本文介绍了价值判决形式主义及其在VJAP系统中的实验实现，它能够论证和预测一组商业秘密盗用案件的结果。 ud udVJAP通过为每个案件创建一个论点图来论证案件。情况下使用一组参数方案。这些方案使用商业秘密法所依据的价值表示以及事实对这些价值的影响。在给定的情况下，VJAP从理论上平衡了影响，并将其模拟为单个先例和这些先例中的价值折衷。它使用自变量图计算出的置信度量度来预测案件结果，并生成证明其预测合理的文本法律论点。置信度传播使用分配给事实对值的影响的定量权重。 VJAP使用迭代优化方法自动从过去的案例中学习这些权重。 ud ud实验评估表明，VJAP生成了基于案例的法律论点，这些案例使合理而明智地使用先例来就案例的异同进行推理。一个先例和两者都包含的价值权衡。与不产生法律依据的机器学习算法相比，VJAP的预测性能很有希望。但是，由于案例数少，因此对预测性能的评估在统计上并不严格。 VJAP表现出的论证和预测行为在某种程度上类似于基于真实案例的法律推理中的现象，例如现实出现的引文图。 ud udVJAP系统和实验表明，可以将符号知识和推理有效地结合起来定量置信度传播。在AI ＆Law中，这样的系统可以包含法律推理的结构，并可以从以前的案例中了解有关领域的定量信息，并可以在新案例的背景下以结构现实的方式应用此信息。
展开▼
