Using NLP to demystify "Terms and Conditions" and summarize the contents
ARodz (~AromaR) |
About a month ago my inbox was flooded with emails beginning with We have decided to update our Terms and Conditions.... Though I am a technical person working in a financial services company and thus terms and conditions are supposed to be my cup of tea, I couldn't get myself to go through any of the actual Terms and Conditions.
A python based Natural Language Processing Engine to summarize the often twisted contents of a legal agreement and defining the pros and cons for the agreement in question for the user would better equip an user to understand what exactly they are agreeing to. This is very important in today's age where we've seen our personal data being breached for the benefit of social media based companies who then sell this data to achieve gains that could be political too. In the financial and legal world such documents are of utmost importance.
The process of developing a solution like this would be about defining the Gives and Takes of an agreement. Every agreement consists primarily of the things that a user is expected to receive from the other party/user and vice versa. The next step would be quantifying that particular give or take. This would give the user an estimate of what he/she would be expected to give/spend. Comparing that with the takes would help the user make a decision as to whether to agree with the terms and conditions or not. The quantifying system could consist of a number of attributes and the "twisted ones" or the ones affecting the user's privacy or other sensitive aspects cold be flagged appropriately so that the user can review and choose.
This talk would talk about the steps, right from defining legal contexts to setting up the words, phrases and understandings for typically legal content.
Anyone who'd want to see themselves make better decisions and understand how agreeing to certain Terms and Conditions could affect their lives and their privacy.
Aroma is a graduate fresh out of the National Institute of Technology, Warangal. As a techno-activist she has been a part of many projects that promote diversity and inclusion. She believes that Automation is the path to Inclusion. In 2016, a teammate of her "Shoes for the Visually Impaired" project presented it at the FOSSASIA. She reads, writes and enjoys walking to explore places. She presently works in a financial services firm and believes that solving problems that she has would solve problems for a large chunk of the world. An ML enthusiast she has about 20+ Coursera Certifications with the respective project work to support her learning in that field. Python is one of her favorite languages and hackathons her favorite party.