AI-Powered Contract Summarization and NLP-Driven Data Cleansing: Innovating Legal Document Analysis

In response to the growing complexity and volume of legal contracts, there is a pressing need for innovative solutions to enhance efficiency and accuracy in drafting processes. This research proposal pivots towards automating language models to summarize existing agreements, with a specific emphasis on data cleansing and summarization of contracts.
The proposed research explores the application of automated language models for contract summarization and data cleansing, aiming to streamline the analysis and interpretation of legal agreements. By leveraging advancements in natural language processing (NLP) and machine learning, the study seeks to develop a framework capable of accurately summarizing complex legal documents while addressing noise, inconsistencies, and ambiguities in the contract texts.
Methodologically, the research will involve preprocessing and analyzing contract documents using state-of-the- art NLP techniques. Language models such as BERT or GPT will be fine-tuned on a dataset of legal agreements to enable accurate contract summarization. Additionally, data cleansing algorithms will be implemented to enhance the quality of extracted information from contracts.

Faculty Supervisor:

Chen Feng

Student:

Partner:

Intell Creative Inc

Discipline:

Engineering

Sector:

Information and cultural industries

University:

The University of British Columbia - Okanagan

Program: