What standard do the grammar tags in the JSON response adhere to?
The standard of the grammar tags is configurable via the feature_standard attribute in the settings argument. We currently support:
- ud – Universal Dependencies tags (default)
- penn – Penn treebank tags
- native – internal codes from Tisane
- description – description of the internal Tisane codes
- glossing – standard glossing abbreviations
As the coverage is concerned, the native codes (and their descriptions) offer the largest number of feature designations, followed by the glossing abbreviations, followed by the Universal Dependencies, and then followed by the Penn treebank tags.