Legal Document Review Task

Context:
- output: Legal Document Review Findings (e.g. with legal document redlines).
- It can (typically) support a Legal Process.
- It can (typically) be performed by a Legal Professional.
- It can (often) follow the creation of an initial Legal Document Draft.
- It can involve Collaboration between legal, business, and other stakeholders.
- It can require research into Legal Research Topics, such as: jurisprudence, case law, regulations, and internal policies.
- It can aim to identify Legal Document Issues, such as: contract risk, inconsistency, error, or non-compliance.
- It can result in Document Revision or Rejection.
- ...
Example(s):
- a Contract Review Task (of legal contracts).
- Regulatory Filing Review (of regulatory filings).
- Policy Review (of legal policies).
- Patent Application Review (of patent applications).
- Settlement Agreement Review (of settle agreements).
- Lawsuit Complaint Review (of lawsuit complaints).
- ...
Counter-Example(s):
- Document Drafting, which creates rather than reviews documents.
- Contract Negotiation, which determines terms through discussion rather than reviewing a draft.
- Legal Discovery, which involves obtaining rather than analyzing documents.
- Litigation, which argues a case in court rather than reviewing documents out of court.
See: Legal Review, Due Diligence, Compliance, Risk Management.

References =

(Wei et al., 2022) ⇒ Fenglong Wei, Haiyang Qin, Shizhuo Ye, Hao Zhao. (2022). “Empirical Study of Deep Learning for Text Classification in Legal Document Review." In: 2018 IEEE International Conference on Big Data (Big Data), pp. 1188-1194. https://doi.org/10.1109/bigdata.2018.8622566
- NOTES: Discusses using convolutional neural networks for text classification and retrieval in legal document review. Results showed CNNs perform better with larger training datasets.

(Yang et al., 2021) ⇒ Ellen Yang, David D. Lewis, Ophir Frieder. (2021). “On Minimizing Cost in Legal Document Review Workflows." In: Proceedings of the 21st ACM Symposium on Document Engineering, pp. 1-4. https://doi.org/10.1145/3465034.3467605
- NOTES: Examines using active learning and human-in-the-loop techniques to minimize the cost of technology assisted review workflows for legal discovery.

(Mahoney et al., 2019) ⇒ C. J. Mahoney, J. Zhang, N. Huber-Fliflet, R. Keeling, S. Levitan. (2019). “A Framework for Explainable Text Classification in Legal Document Review." In: 2019 IEEE International Conference on Big Data (Big Data), pp. 6053-6062. https://doi.org/10.1109/bigdata47090.2019.9006458
- NOTES: Presents an analytics platform for explainable AI text classification models to assist with legal document review.

(Chhatwal et al., 2017) ⇒ R. Chhatwal, N. Huber-Fliflet, R. Keeling, S. Levitan. (2017). “Empirical Evaluations of Active Learning Strategies in Legal Document Review." In: 2017 IEEE International Conference on Big Data (Big Data), pp. 1188-1197. https://doi.org/10.1109/bigdata.2017.8257977
- NOTES: Evaluates different active learning strategies to minimize the cost of legal document review through iterative training.