download-pdfMARKET NEED

Information contained in text documents is central to the legal profession e.g. contracts, end user agreements, industrial regulations etc. Text Analytics and Natural Language Processing (NLP) allow for the automatic extraction and processing of information from text documents. These techniques are increasingly being applied to legal tasks such as contract drafting, automatic compliance checks and extraction of contract elements e.g. contract start and end dates.

TECHNOLOGY SOLUTION

CeADAR’s Text Analytics for Contract Understanding demonstrator application shows how these techniques can be applied to the real world task of mobile app privacy policy analysis. The demonstrator allows the user to input an Android app privacy policy, and it performs an automatic analysis of the practices described therein and visualises the results.

APPLICABILITY

• The web based application can be pointed at any privacy policy URL, or the policy text can be manually entered.

• A machine learning text classifier, trained on the APP-350 corpus, detects aspects of the policy relevant to different privacy areas.

• The application displays the analysis in an easy to interpret visualisation, divided into 1st party and 3rd party practices.

• A more detailed exploration of the distinct privacy clauses related to different privacy aspects is also supported.

Conclusions

The Text Analytics for Contract Understanding demonstrator shows the potential in applying text analytics and NLP techniques for automated contract analysis. Depending on the dataset used, such approaches can be customised for other legal and contractual domains

RESEARCH TEAM

CeADAR Applied Research Group, UCD