Extracting Knowledge Graphs from Financial Filings: Extended Abstract

Textual corpora, such as financial documents, contain a wealth of knowledge. Recently, knowledge graphs have become a popular approach to capturing structured knowledge of entities and their interrelationships. In this paper, we evaluate open information extraction (IE) and knowledge graph construction techniques for assessing the relevance of textual segments in the Financial Entity Identification and Information Integration Challenge. Our approach is to extract several textual signals, including topics and open IE triples, and combine these in a probabilistic framework to predict the relevance of each potential relationship.