Overview of the Text Analytics Workflow
perspective
Create, modify, or test an extractor by using the interface from the Text Analytics Workflow perspective in your Eclipse
development environment.
Creating the Text
Analytics extractor environment You begin with a goal in
mind, such as determining what sites refer to the Watson machine or
conducting a financial analysis on IBM quarterly reports. To
accomplish these goals, you must analyze data, frequently large
amounts of it. Instead, you can create criteria and patterns and use
Text Analytics to help with the analysis.
Labeling the data
You start the extraction plan by labeling snippets of interest and
associated clues. Snippets are words or
phrases that you determine to be helpful to the goal of producing
the information that you need.
Writing the AQL to
extract your labeled examples You can create your AQL
script from a label that you have already identified. It is a good
practice to start from a lower-level label (or bottom-up). For
example, if you have a label that is called Amount and sublabels under that label
called Currency, Number, and Unit,
then you start creating AQL from the Currency,
Number, and Unit labels.
Testing the
extractor After you write AQL statements to extract or
filter text, you can test the extractor by running the AWL from the
InfoSphere BigInsights Tools for
Eclipse and viewing the results.