arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.04262cs.LGcs.IRstat.ML
收藏

从法律文档中提取公平策略

Extracting Fairness Policies from Legal Documents

IIIT Delhi(德里印度理工学院);IBM Research(IBM研究院)

Rashmi Nagpal, Chetna Wadhwa, Mallika Gupta, Samiulla Shaikh, Sameep Mehta, Vikram Goyal

摘要:

机器学习社区最近正在探索偏见和公平性对人工智能应用的影响。这些应用的公平性定义根据其应用领域而有所不同。在给定上下文中管理这种机器学习系统的使用的策略由国家的宪法法律和由参与使用的组织执行的监管策略来定义。与公平相关的法律和政策通常分布在宪法、协议和组织条例等大型文件中。这些法律文件具有较长的复杂句子,以实现严谨性和健壮性。自动提取公平策略,或者一般来说,从大型法律语料库中提取任何特定类型的策略,对于研究人工智能应用背景下的偏见和公平性非常有用。我们试图自动提取公平政策,从公开的法律文件使用两种方法的基础上语义相关性。实验揭示了经典的基于Wordnet的相似性和基于向量的相似性在解决这个任务方面的不同。我们已经证明,基于词向量的相似性以较大的幅度击败了经典方法,而其他意义和句子的向量表示甚至无法匹配经典基线。此外,我们还提供了全面的错误分析和推理,以通过数据集中的适当示例解释结果,以获得更深入的见解。

英文摘要:

Machine Learning community is recently exploring the implications of bias and fairness with respect to the AI applications. The definition of fairness for such applications varies based on their domain of application. The policies governing the use of such machine learning system in a given context are defined by the constitutional laws of nations and regulatory policies enforced by the organizations that are involved in the usage. Fairness related laws and policies are often spread across the large documents like constitution, agreements, and organizational regulations. These legal documents have long complex sentences in order to achieve rigorousness and robustness. Automatic extraction of fairness policies, or in general, any specific kind of policies from large legal corpus can be very useful for the study of bias and fairness in the context of AI applications. We attempted to automatically extract fairness policies from publicly available law documents using two approaches based on semantic relatedness. The experiments reveal how classical Wordnet-based similarity and vector-based similarity differ in addressing this task. We have shown that similarity based on word vectors beats the classical approach with a large margin, whereas other vector representations of senses and sentences fail to even match the classical baseline. Further, we have presented thorough error analysis and reasoning to explain the results with appropriate examples from the dataset for deeper insights.

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。

↑