IBM BigInsights Text Analytics (V4)

Learn how to use IBM® BigInsights® Text Analytics, an information extraction system, to extract information from unstructured and semi-structured documents.

Using IBM BigInsights Text Analytics you can create extractors using a visual web interface. The visual extractors are then automatically translated into Annotation Query Language (AQL) rules to extract structured information from unstructured and semi-structured documents. You can apply Text Analytics to big data at rest in IBM BigInsights and big data in motion in IBM Streams.

Profil uczestnika

The course is designed for data scientists and developers who want to use Text Analytics.

Agenda

• Understand and describe the need for text analytics
• Understand the Annotation Query Language (AQL)
• Describe the AQL data model
• Text Analytics web tooling
• Navigate a Text Analytics project in the web UI
• Import documents into a project
• Understand the Text Analytics development process
• Use the tooling to create and test extractors

Wymagane przygotowanie uczestników

• Students should be familiar with SQL, Hadoop, and the Linux file system.
• Have taken DW601 – IBM BigInsights Overview
• Although not required, it would also be helpful for students to take the DW644 – IBM BigInsights Bigsheets to have a better understanding of how BigSheets can work with Text Analytics. 

Zagadnienia

• Understand and describe the need for text analytics
• Understand the Annotation Query Language (AQL)
• Describe the AQL data model
• Navigate a Text Analytics project in the web UI
• Import documents into a project
• Understand the Text Analytics development process
• Use the tooling to create and test extractors