A1: Systematic Content Analysis of Litigation Events (SCALES) Open Knowledge Network to Enable Transparency and Access to Court Records

A1：诉讼事件的系统内容分析 (SCALES) 开放知识网络，以实现法庭记录的透明度和访问

• 批准号: 2033604
• 负责人: Luis Amaral
• 金额: $ 499.98万
• 依托单位: Northwestern University
• 依托单位国家: 美国
• 项目类别: Cooperative Agreement
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-09-01 至 2024-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2033604&HistoricalAwards=false
• 关键词: A1; Systematic; Content; Analysis; Litigation

The NSF Convergence Accelerator supports use-inspired, team-based, multidisciplinary efforts that address challenges of national importance and will produce deliverables of value to society in the near future.This project will develop the Systematic Content Analysis of Legal EventS Open Knowledge Network (SCALES OKN). The SCALES OKN seeks to create the computational and data science tools needed to democratize access to court records. Greater access to court records and analysis tools will enable policy makers, scholars, journalists, entrepreneurs, and the public to directly engage with and evaluate the workings of the U.S. courts. The U.S. court system collects detailed data about their activities, but the challenge is that most of this data sits behind paywalls and in scattered systems that are difficult to access. Highly limited access means that court records are functionally inaccessible to the public. This limited access to court records has prevented the development of tools to turn court data into information and insights. The SCALES OKN will develop aggregation and analysis tools that will bring together a community of public servants, academic institutions, non-profits, private organizations, and individuals to better understanding how litigation proceeds. Access to these new data and analysis tools will enable legal scholars to better analyze litigation processes, entrepreneurs to assess litigation costs and risk, journalists to investigate equity in outcomes, advocacy organizations assess public policy needs, and the public to better understand how the modern judiciary functions.This project joins 22 scholars in computer and data science, economics, journalism, law, and sociology from eight universities with a large and diverse range of partners from non-profit and for-profit organizations. The SCALES OKN’s existing partnerships will enable users to ask questions such as how lawsuits involving Fortune 500 companies or with representation from large law firms progress, or if judicial rules are consistently implemented. As the project develops, additional data and tools will enable an even richer view into topics such as how new laws impact the judiciary, corporations, and individuals, or how a changing economic climate impacts people and organizations—whether that be because of a global economic downturn or changes to the nature of employment as impacts from the COVID-19 epidemic unfold.This team is building SCALES OKN as an open and freely accessible knowledge network. Their efforts include developing the tools to transform the data that define court records into actionable information. This work will include the development of tools to extract and transform data from court records, resolve and disambiguate entities, and enable the automated identification of litigation events and construction of a lawsuit’s lifecycle. Rather than having users depend on their own data skills, the SCALES efforts plan to map user information requests onto the analyses needed to address questions of relationships, correlations, trends, and distributions of actions and decisions in the legal system. The team also plans to build tools that facilitate the continued growth of open knowledge networks through public contributions. The project will leverage machine learning to enable users to develop further ontologies and merge additional datasets to answer novel questions. Importantly, these advances will allow for the rapid expansion of natural language processing techniques to legal contexts and catalyze further computational analysis of the law.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

美国国家科学基金会融合加速器支持使用启发，团队为基础，多学科的努力，解决国家的重要性的挑战，并将产生交付价值的社会在不久的将来。该项目将开发系统内容分析的法律的事件开放知识网络（SCALES OKN）。SCALES OKN旨在创建使法院记录的访问民主化所需的计算和数据科学工具。更多地使用法院记录和分析工具将使政策制定者、学者、记者、企业家和公众能够直接参与和评估美国法院的工作。美国法院系统收集有关其活动的详细数据，但挑战在于，这些数据大多位于付费墙之后，并且分散在难以访问的系统中。高度限制的查阅意味着公众在功能上无法查阅法院记录。这种对法庭记录的有限访问阻碍了将法庭数据转化为信息和见解的工具的开发。SCALES OKN将开发汇总和分析工具，将公务员，学术机构，非营利组织，私人组织和个人聚集在一起，以更好地了解诉讼如何进行。获得这些新的数据和分析工具将使法律的学者能够更好地分析诉讼过程，企业家能够评估诉讼成本和风险，记者能够调查结果的公平性，倡导组织评估公共政策需求，公众能够更好地了解现代司法机构如何运作。该项目将与计算机和数据科学，经济学，新闻学，法律，来自八所大学的社会学和社会学，以及来自非营利和营利组织的广泛而多样化的合作伙伴。SCALES OKN现有的合作伙伴关系将使用户能够提出问题，例如涉及财富500强公司或大型律师事务所代表的诉讼如何进行，或者司法规则是否得到一致执行。随着项目的发展，更多的数据和工具将使人们能够更丰富地了解诸如新法律如何影响司法机构、公司和个人等主题，或者不断变化的经济气候如何影响人们和组织-无论是因为全球经济衰退还是新冠肺炎影响下就业性质的变化-19疫情展开。该团队正在将SCALES OKN打造成一个开放且可免费访问的知识网络。他们的努力包括开发工具，将定义法庭记录的数据转换为可操作的信息。这项工作将包括开发工具，从法庭记录中提取和转换数据，解决和消除实体的歧义，并实现诉讼事件的自动识别和诉讼生命周期的构建。SCALES计划不是让用户依赖自己的数据技能，而是将用户的信息请求映射到所需的分析上，以解决法律的系统中行动和决策的关系、相关性、趋势和分布等问题。该小组还计划通过公众捐款建立促进开放知识网络持续增长的工具。该项目将利用机器学习使用户能够开发进一步的本体并合并额外的数据集来回答新的问题。重要的是，这些进步将使自然语言处理技术迅速扩展到法律的环境，并促进对法律的进一步计算分析。该奖项反映了NSF的法定使命，并被认为值得通过使用基金会的智力价值和更广泛的影响审查标准进行评估来支持。

项目成果

A user-centered approach to developing an AI system analyzing U.S. federal court data

• DOI: 10.1007/s10506-022-09320-z
• 发表时间: 2022-08
• 期刊: Artificial Intelligence and Law
• 影响因子: 4.1
• 作者: Rachel F. Adler;Andrew R. Paley;A. L. Li Zhao;Harper Pack;Sergio Servantez;Adam R. Pah;K. Hammond;S. O. Consortium

PRESIDE: A Judge Entity Recognition and Disambiguation Model for US District Court Records

PRESIDE：美国地方法院记录的法官实体识别和消歧模型

• DOI: 10.1109/bigdata52589.2021.9671351
• 发表时间: 2021
• 期刊: 2021 IEEE International Conference on Big Data (Big Data
• 作者: Pah, Adam R.;Rozolis, Christian J.;Schwartz, David L.;Alexander, Charlotte S.;Okn Consortium, Scales
• 通讯作者: Okn Consortium, Scales

From data to information: automating data science to explore the U.S. court system

从数据到信息：自动化数据科学探索美国法院系统

• DOI: 10.1145/3462757.3466100
• 发表时间: 2021
• 期刊: ICAIL '21: Proceedings of the Eighteenth International Conference on Artificial Intelligence and Law
• 作者: Paley, Andrew;Zhao, Andong L.;Pack, Harper;Servantez, Sergio;Adler, Rachel F.;Sterbentz, Marko;Pah, Adam;Schwartz, David;Barrie, Cameron;Einarsson, Alexander
• 通讯作者: Einarsson, Alexander

The Promise of AI in an Open Justice System

人工智能在开放司法系统中的前景

• DOI: 10.1002/aaai.12039
• 发表时间: 2022
• 期刊: AI Magazine
• 影响因子: 0.9
• 作者: Pah, Adam R;Schwartz, David L;Sanga, Sarath;Alexander, Charlotte S;Hammond, Kristian J;Amaral, Luís A.N.
• 通讯作者: Amaral, Luís A.N.