In order to more efficiently catalogue many texts into subjects, Melingo created the Text Tagger. Text Tagger is a web-based tool which receives a text as input, and outputs a list of its prominent textual entities. The system also outputs HTML keyword tags which include these entities, for use in website building and promoting. The tags are automatically chosen according to criteria, and include texts of names, place names, names of organizations and a variety of other subjects. The system can be edited and tags can be added according to the user’s needs.
Characterisitics of Melingo’s Text Tagger
Identification of entities from a broad world of concepts
Text Tagger can identify entities from many built in categories without manual definition. Among the entities: Names of countries, cities and people, medical terms, weapons, names of organizations and more.
Automatically create HTML tags
Text Tagger automatically creates HTML keyword tags for any document, allowing it to be immediately put online.
Text Tagger can be personalized and adapted to the needs of the customer and to his world of content, giving preference to concepts from his world. The customer can also define new concepts to be identified according to his needs.
Use of morphology
Concepts are identified in the text even when used in different conjugations, spellings and forms, in a way which ensures optimal recognition of the central concepts of the text and the number of times they recur.
Example of Text Tagger function
In the following example the four central concepts were extracted from an article. Additionally, the system automatically created HTML keywords for cataloguing according to the main concepts.