Text Mining 360° Portuguese
Skill Cartridge®
Extracts and normalizes more than 20 types of specific entities related to Portuguese, among which the names of People, Companies, Organizations, Locations, as well as Measurements, Money, Time expressions and Contact information.
By Manchete

"Text Mining 360° Portuguese (TM360-Port) extracts and normalizes more than 20 types of specific entities related to Portuguese, among which the names of People, Companies, Organizations, Locations, as well as Measurements, Money, Time expressions and Contact information. To achieve this task, TM360-Port embeds a variety of predictive natural language processing methods including morphological and syntactical heuristics, lexicon analysis and statistical methods. TM360-Port can be customized through Luxid® Knowledge Editor, for example to add vocabularies or patterns of interest as well as new entity types specific to the Portuguese language. Especially suited to extract information on well-formed texts, TM360-Port is also used on different kinds of corpus, like enterprise content. Three procedures are available: NER: Main and default one, it is completely dedicated to entity extraction. RF360: In addition to entity extraction, this procedure also extracts relationships between major entities (People, Companies, Locations, Organizations) when separated by a verb. The relation name is the verb one. RF360Plus: Same as RF360 adding unspecified proper nouns as relationship triggers. A fourth one, the SkillUnit procedure, is available for developpers only and allows to see the extraction results from a tree perspective instead of a graph. Some limitations on major entities scope: - TM360-Port is a customer product, its structure is different from the the regular TM360, that is why it is not possible to use the basic plugin which allows mapping between a family name and the corresponding first name + family name association. - This SC is specific to the customer who designed it, hence no parameters are available for tuning, unlike the regular TM360. - Contrary to TM360, TM360-Port allows you to extract some family names alone as a ""Person"" entity."

Skill cartridge
Generic
Language(s): PT
Compatibility: Luxid® 5.0
Posting date: January 2013
Version: 6.0
Business model: Turnkey