Detecting and explaining unfairness in consumer contracts through memory networks

Artificial Intelligence and Law 30 (1):59-92 (2021)
  Copy   BIBTEX

Abstract

Recent work has demonstrated how data-driven AI methods can leverage consumer protection by supporting the automated analysis of legal documents. However, a shortcoming of data-driven approaches is poor explainability. We posit that in this domain useful explanations of classifier outcomes can be provided by resorting to legal rationales. We thus consider several configurations of memory-augmented neural networks where rationales are given a special role in the modeling of context knowledge. Our results show that rationales not only contribute to improve the classification accuracy, but are also able to offer meaningful, natural language explanations of otherwise opaque classifier outcomes.

Links

PhilArchive



    Upload a copy of this work     Papers currently archived: 90,616

External links

Setup an account with your affiliations in order to access resources via your University's proxy server

Through your library

Similar books and articles

Ambivalences in Consumer Law: Remarks on the Effects of Writing the Law.Vincent Forray - 2013 - Jurisprudencija: Mokslo darbu žurnalas 20 (3):971-1003.
Theoretical and Practical Issues of Consumer's Conception.Lina Novikovienė - 2010 - Jurisprudencija: Mokslo darbu žurnalas 122 (4):279-293.
More than working memory rides on long-term memory.Joaquín M. Fuster - 2003 - Behavioral and Brain Sciences 26 (6):737-737.
Out of their minds: Legal theory in neural networks. [REVIEW]Dan Hunter - 1999 - Artificial Intelligence and Law 7 (2-3):129-151.
On Legal Interpretation of Basic Consumer Rights.Teresa Mróz - 2013 - Studies in Logic, Grammar and Rhetoric 32 (1):9-23.
What is Interpretability?Adrian Erasmus, Tyler D. P. Brunet & Eyal Fisher - 2021 - Philosophy and Technology 34:833–862.
A Consumer Perspective on Forensic DNA Banking.Sharon F. Terry & Patrick F. Terry - 2006 - Journal of Law, Medicine and Ethics 34 (2):408-414.

Analytics

Added to PP
2021-05-12

Downloads
8 (#1,138,679)

6 months
5 (#247,092)

Historical graph of downloads
How can I increase my downloads?