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