Textual ETL – Preparing text for analysis with Tiger Graph

What inspired you, what did you learn, how you built your project and challenges faced Text is the informational lifeblood of the corporation. But text is not used in decision making, and it ought to be. Early approaches to trying to work with text such as NLP are complex, academic, and expensive, as well as time consuming. There needs to be a commercial product that cuts through the complexity and hassle of NLP. With textual ETL you can go directly from raw text into a knowledge graph in a matter of minutes. Textual works on any form of text – from the Internet, email, voice recordings, printed reports. etc. Textual ETL works in the medical records environment. Textual ETL can do sentiment analysis to hear the voice of the customer. Other places where textual works in are corporate contracts, warranty claims, insurance claims, and in many other environments. Built with - what languages, frameworks, platforms, cloud services, databases, API’s or other technologies did you use? Textual ETL is built in a Microsoft vb.net framework using a SQL data base. The code that textual ETL is written in includes vb.net. Textual ETL operates in the cloud as a service. Textual ETL includes deidentification technology, sentiment analysis, corelative analysis among others. Textual ETL has developed the ontology for comprehensive medical terminology. Textual ETL has seamlessly interfaced with Tiger Graph and has enabled Tiger Graph to be used analytically in the health care space. Textual ETL works in multiple languages such as English, Spanish, Portuguese, Italian, German, French, Dutch, and so forth.

Built With

• .net
• and
• c#
• framework
• vb.net
• with