PhD Research Seminar: Regulatory Text Analysis, Importance Assessment in Multiplex Networks
First talk: An Overview of Problems and Methods of Regulatory Text Analysis
Speaker: Denis Smirnov, third-year PhD student, Faculty of Computer Science
Regulatory pressure from governments is growing around the world. Both regulators and companies look for ways to optimize regulatory burden and explore NLP methods to reduce human costs throughout this process. Most of the modern NLP models are trained on general web texts and cannot be easily applied to complex legal documents, which are different in structure and vocabulary. This talk presents an overview of problems and NLP methods in RegTech domain. The talk highlights domain-specific challenges and provides a detailed description of particular cases.
Second talk: Belief Functions for the Importance Assessment in Multiplex Networks
Speaker: Natalia Meshcheryakova, second-year PhD student, Faculty of Economic Sciences
Dempster-Shafer theory of belief functions is a widely used tool to measure belief or conflict between elements in a considered system. Recently it has also found use in the field of social network analysis. We apply Dempster-Shafer theory in order to reveal important elements in undirected weighted networks. The proposed approach is also adapted to multiplex structures where elements can interact on different levels. Additionally, we provide analytical relations between a proposed measure and classical centrality measures for particular graph configurations.
In this talk we will shortly discuss some core definitions from the theory of belief functions and network analysis and present a novel model for the importance assessment in networks.