Linguistic Tools

With a wide experience in research, we offer installation, support and customization of:

  • DepPattern. Linguistic package providing a grammar compiler (PoS taggers) and dependency based parsers for several languages: English, Portuguese, Spanish, French, Galician.
  • GaleXtra. Multiword extractor for English, Portuguese, Spanish, French, Galician.
  • Lingua Toolkit. Natural Language kit containing a dependency parser and a thesaurus generator. Languages: English, Portuguese, Spanish, French, Galician.
  • QueLingua. Languages: English, Portuguese, Spanish, French, Galician RAG, Galician AGAL.
  • Standard document classifier. Language independent.
  • Cluster and labelling of documents. Language independent.
  • NEC (Named Entity Classification). Languages: Portuguese, Galician, Spanish.
  • DepOE. Triplets extraction based on Open Information Extraction. Languages: Portuguese, Galician, Spanish, English, French.
  • RSScrawler. RSS crawler and scrapper software to create a corpus from a list of urls.
  • CorpusPedia. Corpus builder from Wikipedia.

Contact us for more information.