- 23 June, 2014
- 0 Comments
New information technologies are more and more present in our daily life. There are few areas that are not integrated with the computer tecnology. However, there is a segment that barely was explored by ICT: the human language. For this reason, Cilenis equipment and the USC’s research group, ProLNat, work together to offer a single platform, result of the combination of human language and computer technology: Linguakit.
Today released the Named Entity Recognizer. This tool allows you to extract the names of person, place, organization, quantities and dates from a text; in a completely automatic way. It means, introducing a text we know automatically who it is, where it is, which organization is, when it spent and what amounts there are in the text. Linguakit’s Name Entity Recognizer is available for English, Spanish, Portuguese and Galician; like most of Cilenis’ developments.
Name Entity Recognizer works with a model which combines morphosyntactic analysis with learning algorithms, therefore, according to the type of word, the context, the grammatical position, NER algorithm is able to find entities that appear in a written text and it can also classify them (NEC) as persons, organizations, places, dates or amounts. And like all modules in Linguakit, is available for companies at CilenisAPI that allows to apply massively the NER to large groups of textual information, call Big Data.
Don’t waste more time and discover the advantages of using NER. You will save many time and you will obtain a lot of information.