Add Dictionary Features

You can add dictionary features either by choosing from suggested features when there is a conflict or by defining your own dictionary for a concept in your business domain. When reviewing a suggested dictionary item, a pop-up with the suggested phrases will appear.

Clicking a suggestion will open a popup where you can add it as a new feature or add the suggested phrases to an existing feature. The "Feature details" tab shows the phrases in the dictionary and the entity/sub-entity the feature is suggested for. You can associate one feature with more entities as you see applicable. The dictionary phrases are tokens that, if found in a document, will trigger this feature.

You can delete some of the suggested phrases by clicking on the little "X" on the phrase. You can also add additional phrases by typing them in a comma-separated way in the phrase text box.

When you are defining your own dictionary feature, give your feature a name and select the schema entity that the feature should associate with. Add a few phrases that represent the concept by typing them as comma separated and press "Add Phrases". For instance, if trying to define a dictionary item called "Street", you may include "Street" as a dictionary item, with synonyms like "Avenue", "Parkway" and "Boulevard".
If you want to add a comma as a dictionary phrase, surround it with quotation marks.

Once you add few phrases to the dictionary, you can use "Generate Synonyms" to quickly populate your dictionary.

You can include variations of the dictionary phrases at the bottom of the widget, and select any relevant choices. "Ignore case" is always selected by default. Those listed are:
a. Ignore Case
b. Ignore Digit Identity
c. Ignore Tense
d. Ignore Plurals
e. Ignore Typos

The "Feature Matching Options" tab enables you to specify the position of the feature with respect to the entity it is associated with. There are six options. You can select one or more options at the same time.
a. "Inside" means the feature fires if one of its phrases exist within the boundary of the entity segment.
b. "Exact match" means the feature fires if one of its phrases exactly matches the entity segment.
c. "Begins" means the feature fires if one of its phrases takes place at the beginning of the entity segment.
d. "Ends" means the feature fires if one of its phrases takes place at the end of the entity segment.
e. "Follows" means the feature fires if one of its phrases exactly follows the entity segment.
f. "Precedes" means the feature fires if one of its phrases exactly precedes the entity segment.

Once finished, press the "Add New" at the bottom of the screen.