Knowledge Base Creation

PDF Transcript:

Is this what you were imagining?

We want to lead our industry in tapping our own data resources because we believe it will help us understand our business and drive its success.

We understand a graph database is the latest way to connect the data dots, but the only data we have is structured or in an existing database. We want to expand on that and include new ideas and concepts from other sources.

Lymba Knowledge Base Creation

In large organization, graph databases are beginning to be used instead of relational databases for speedier performance and to find and set relationships among the data. This allows a company to rapidly expand how much it knows about its data and its business.

Structured data will be easy to identify and transform for the graph. Think go a database of employee information, or perhaps offline client lists. On the other hand, all of the emails your employees sent to shoe clients are unstructured and no usable data can be derived from its contents or stored in the graph.

A wealth of knowledge lives in the vast amount of text-centric data we collect, just like those emails. Lymba extracts and stores it in your graph database. A graph is the perfect place to store and maintain data relationships.

Now, you can use Lymba’s NLP Pipeline K-Extractor to pull knowledge out of…

• Regulations - compare your actual activity against compliance needs

• Internal research reports - semantically search and find the information you have self-created

• Contracts and leases - extract pertinent information for analysis

• Externally published data - access to data on the web to be searched semantically

• Specs, financials, etc. with tables - extract information from tables

• Emails, reviews and tweets - social sentiment or customer feedback

• Large document repositories

• And many more: risk data, IOT data, project data, expert data…

Lymba is trained to understand your domain. The data is pushed through a series of increasingly complex analyses and the end result is digitized knowledge. Specifically, we train the system by building or leveraging an ontology, annotating documents, or configuring system rules using an open architecture.

The system can integrate with any graph. The final step in the pipeline converts the knowledge into RDF triples for ingestion by your graph.

Organizations can now build a truly deep knowledge base to make quicker, more thoughtful decisions about their business with Lymba’s tools for knowledge base extraction and integration.