The PoS Tagging of Linguakit.

  • 30 June, 2014
  • Linguakit

Cilenis’ team and the USC’s research group, ProLNat, struggle daily by offer you a quality product. For this reason, every week we try to provide you with a new linguistic tool to complete the package that will shape to Linguakit. Therefore, today we adds to this portal, one more linguistic tool: the PoS Tagging, available in Galician, Spanish, Portuguese and English. The main function of this module is the textual analysis through the labelling of all the words in a text.

How does this tool work?

The PoS Tagging recognizes the origin of any word until it gets to its primitive form. It gives you morphological information of each word: from a verb conjugation it will give you its infinitive and it classified it according to its form, person and tense of the verb; from a contraction it will indicate you how many parts it is, analysing in morphologically terms each one. And so with all the words in the text.

The PoS Tagging of Linguakit is built from several FreeLing modules: the Part of Speech Tagging, main module of this tool, the entities recognizer and the recognizer of locutions. With the Part of Speech Tagging, it labels each word of the text and provides the morphological information and the grammatical category of each term. This is adapted to users so the labels are more recognizable by any person. In addition, through the entities recognizer, the PoS Tagging is able to identify how a single watchword, simple or composite names (Felipe VI), and locutions.

Discover the many benefits of employing the PoS Tagging. Enters on and become an active user of these linguistic tools. You won’t regret it!

We come back soon with more news.