...
In a basic implementation, NLP uses content, context and syntax to identify text strings that fall into what are called Default Named Entities. The categories Voyager uses are listed below, as well as the corresponding field names. Note that the special field nlp_place is the only field used for geotagging, while all fields can be used in refining search results.
Category Name | Field Name |
Administrative Places | nlp_admin_places |
Art | nlp_art |
Events | nlp_events |
Facilities | nlp_facilities |
Geographic Places | nlp_geo_places |
Groups | nlp_groups |
Languages | nlp_languages |
Legal References | nlp_legal |
Companies and Organizations | nlp_orgs |
People | nlp_people |
Products | nlp_products |
NLP Place (used for geotagging) | nlp_place |
Viewing NLP Results
After you have enabled NLP and rescanned the location, you can find NLP-derived fields on the Detail Page of a record, for example:
...
In Voyager, adding an NLP pipeline step greatly improves accuracy when identifying the most-relevant search results. You You can also use the results of NLP to improve geotagging results. Note that NLP is a language- and text-based process, so there will no benefit with datasets that do not contain text information.
Voyager's standard installation includes the NLP extension, but you will need to download a separate Python library before you can use it with your data. See Downloading and Installing the Natural Language Processing Python File for more information.
See Also
...