Contracts are complex, multi-dimensional objects expressed in legal language, traditionally realized in documents that form the foundation of global commerce. To process a contract, a human being must begin by understanding: by applying linguistic skills to read and parse the form and syntax of the legal language. Its complex, laborious and error-prone exercise, requiring high level of tenacity and expertise.

How does AI aid in navigating in their complex worlds?

How does Machine Learning, Deep Learning and Natural Language Processing is used in legal text mining/processing?

This talk is about how AI is leveraged in finding answers to above questions with specific case studies from Icertis's Contract Management platform.

Various applications need lower dimensional representation of shapes. Midcurve is one- dimensional(1D) representation of a two-dimensional (2D) planar shape. It is used in applications such as animation, shape matching, retrieval, finite element analysis, etc. Methods available to compute midcurves vary based on the type of the input shape (images, sketches, etc.) and processing approaches such as Thinning, Medial Axis Transform (MAT), Chordal Axis Transform (CAT), Straight Skeletons, etc., all of which are rule-based.

This presentation talks about a novel method called MidcurveNN which uses Encoder-Decoder neural network for computing midcurve from images of 2D thin polygons in supervised learning manner. This dimension reduction transformation from input 2D thin polygon image to output 1D midcurve image is learnt by the neural network, which can then be used to compute midcurve of an unseen 2D thin polygonal shape.