JSI at the FinSim-2 task: Ontology-Augmented Financial Concept Classification

TL;DR

This paper demonstrates how ontologies can be used for financial concept classification by transforming ontologies into graphs, applying semantic generalization, and combining graph search with word vectorization and machine learning.

Contribution

It introduces a practical ontology-based approach for classifying financial concepts into relevant hypernyms without requiring training data.

Findings

Effective classification of financial concepts into hypernyms

Combines graph search with word vectorization and machine learning

Achieves promising results on the FinSim-2 task

Abstract

Ontologies are increasingly used for machine reasoning over the last few years. They can provide explanations of concepts or be used for concept classification if there exists a mapping from the desired labels to the relevant ontology. Another advantage of using ontologies is that they do not need a learning process, meaning that we do not need the train data or time before using them. This paper presents a practical use of an ontology for a classification problem from the financial domain. It first transforms a given ontology to a graph and proceeds with generalization with the aim to find common semantic descriptions of the input sets of financial concepts. We present a solution to the shared task on Learning Semantic Similarities for the Financial Domain (FinSim-2 task). The task is to design a system that can automatically classify concepts from the Financial domain into the most relevant hypernym concept in an external ontology - the Financial Industry Business Ontology. We propose a method that maps given concepts to the mentioned ontology and performs a graph search for the most relevant hypernyms. We also employ a word vectorization method and a machine learning classifier to supplement the method with a ranked list of labels for each concept.