On the Text links tab, you can build and explore text link analysis patterns found in your text data. Text link analysis (TLA) is a pattern-matching technology that enables you to define TLA rules and compare them to actual extracted concepts and relationships found in your text.
Patterns are most useful when you are attempting to discover relationships between concepts or opinions about a particular subject. Some examples include wanting to extract opinions on products from survey data, genomic relationships from within medical research papers, or relationships between people or places from intelligence data.
After you've extracted some TLA patterns, you can explore them and even add them to categories. To extract TLA results, there must be some TLA rules defined in the resource template or libraries you're using.
With no type patterns selected, you can click the Settings icon to change the extraction settings. For details, see Setting options. You can also click the Filter icon to filter the type patterns that are displayed
Type pattern pane
You can explore and select your TLA pattern results using the Type pattern pane. Patterns are made up of a series of up to either six types or six concepts. The TLA pattern rule as it's defined in the linguistic resources dictates the complexity of your pattern results.
Pattern results are first grouped at the type level and then divided into concept patterns.
- Type patterns. The Type
pattern pane presents extracted patterns consisting of two or more related types
matching a TLA pattern rule. Type patterns are shown as
<Organization>+<Location>+<Positive>, which might provide positive feedback about an organization in a specific location. - Concept patterns. From the
Preview tab, click Review concepts to open the
Concepts tab. The Concepts tab presents the extracted
patterns at the concept level. Concept patterns follow a structure such as
hotel + paris + wonderful.
Preview pane
The preview area presents the extraction results. Just as with the extraction results on the Concepts and Categories tabs, you can review and refine the results here, or refine the results directly in the Resource editor, and then re-extract your patterns.