Knowledge Extraction and Applications utilizing Context Data in Knowledge Graphs

Abstract

Context is widely considered for NLP and knowledge discovery since it highly influences the exact meaning of natural language. The scientific challenge is not only to extract such context data, but also to store this data for further NLP approaches. Here, we propose a multiple step knowledge graphbased approach to utilize context data for NLP and knowledge expression and extraction. We introduce the graph-theoretic foundation for a general context concept within semantic networks and show a proof-of-concept-based on biomedical literature and text mining. We discuss the impact of this novel approach on text analysis, various forms of text recognition and knowledge extraction and retrieval.

An efficient approach towards the generation and analysis of interoperable clinical data in a knowledge graph

“…However, we need to create a more generic schema for the graph database. Therefore, we extend the schema from [11] by combining all blue marked entities from Fig. 6.…”

“…In these and other common settings pathway databases play an important role. As a basis, biomedical literature and text mining are used to build knowledge graphs, see [11]. As part of the studies on integrative data semantics within clinical research, data on patients suffering from certain diseases have been collected by various institutions.…”

“…The testing system is based on Neo4j and holds a dense large-scale labeled property graph with more than 71M nodes and 850M edges. They are based on biomedical knowledge graphs as described in [11].…”

Knowledge Detection and Discovery using Semantic Graph Embeddings on Large Knowledge Graphs generated on Text Mining Results

“…Several ontologies and terminologies were added to the knowledge graph, for example Computer Science Ontology (CSO, see http://cso.kmi.open.ac.uk/home), HUGO Gene Nomenclature Committee (HGNC, see [24]), Gene Ontology (GO, see [25] and [26]) or Disease Ontology (DO), see [27]). These ontologies can be used to annotate context with methods from text mining to data entities within the graph, see [6].…”

“…The testing system is based on Neo4j and holds a dense large scale labeled property graph with more then 75M nodes and 960M edges. This graph is based on biomedical knowledge graphs as described in [6] and [7].…”