Conversation Concepts: Understanding Topics and Building Taxonomies for Financial Services

Abstract

Knowledge graphs are proving to be an increasingly important part of modern enterprises, and new applications of such enterprise knowledge graphs are still being found. In this paper, we report on the experience with the use of an automatic knowledge graph system called Saffron in the context of a large financial enterprise and show how this has found applications within this enterprise as part of the “Conversation Concepts Artificial Intelligence” tool. In particular, we analyse the use cases for knowledge graphs within this enterprise, and this led us to a new extension to the knowledge graph system. We present the results of these adaptations, including the introduction of a semi-supervised taxonomy extraction system, which includes analysts in-the-loop. Further, we extend the kinds of relations extracted by the system and show how the use of the BERTand ELMomodels can produce high-quality results. Thus, we show how this tool can help realize a smart enterprise and how requirements in the financial industry can be realised by state-of-the-art natural language processing technologies.

Covid19/IT the digital side of Covid19: A picture from Italy with clustering and taxonomy

“…McCrae et at. [ 52 ] report on their experiments exploiting the tool Saffron to extract a taxonomy from a text corpus in the context of financial enterprise, discussing on how the extract knowledge graph can be used. Treeratpituk et al [ 53 ] propose a graph-based approach for constructing concept hierarchy from a text corpus.…”

Application of AI technology in personalized recommendation system for financial services

“…In the era of financial technology, more and more financial services will gradually realize data, standardization, and intelligence. When the development reaches a certain stage, the existing technical bottlenecks of financial institutions will no longer exist, and the competition of financial institutions in the future will largely rely on the customization of personalized services [3][4]. By constructing data models and building network platforms to provide investors with intelligent financial advisory services, it can, to a certain extent, replace traditional manual investment advisors [5].…”