PROJECT TITLE :
Building and Querying an Enterprise Knowledge Graph - 2017
ABSTRACT:
Given knowledge reaching an unprecedented amount, coming from diverse sources, and covering a selection of domains in heterogeneous formats, data suppliers are faced with the essential challenge to method, retrieve and gift information to their users so as to satisfy their advanced info wants. In this paper, we gift Thomson Reuters’ effort in developing a family of services for building and querying an enterprise knowledge graph in order to deal with this challenge. We have a tendency to 1st acquire data from numerous sources via different approaches. Furthermore, we mine useful info from the information by adopting a variety of techniques, together with Named Entity Recognition and Relation Extraction; such mined info is additional integrated with existing structured knowledge (e.g., via Entity Linking techniques) in order to obtain relatively comprehensive descriptions of the entities. By modeling the data as an RDF graph model, we have a tendency to enable easy data management and the embedding of made semantics in our knowledge. Finally, so as to facilitate the querying of this mined and integrated data, i.e., the information graph, we propose TR Discover, a natural language interface that enables users to ask questions of our information graph in their own words; these natural language questions are translated into executable queries for answer retrieval. We evaluate our services, i.e., named entity recognition, relation extraction, entity linking and natural language interface, on real-world datasets, and demonstrate and discuss their practicability and limitations.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here
