Demos & Resources

TUNER has developed technologies and resources that have been integrated in different system demonstrations and tools. Here you can access them.

DEMOS

  • UMLS Mapper: http://demos-v2.vicomtech.org/umlsmapper (user: vicomtech  & password: umlsmapper). UMLS Mapper identifies medical terms in free text in Spanish and map them to concepts of the UMLS medical terminology compendium. 
  • AsisTerm: http://scientmin.taln.upf.edu/scielo is a prototype aimed to facilitate the understanding of complex biomedical terms in short texts -currently, abstracts of articles in English and Spanish from the ScieLO parallel corpu- by means of the identification and annotation of UMLS concepts and the automatic expansion of their definitions.
  • Lingaliza: http://sli.uvigo.gal/lingaliza/ is a web interface designed to test the full new set of NLP tools provided by the IXA pipes for the Galician language. 
  • Analhitza: http://ixa2.si.ehu.es/clarink/analhitza.php is a web interface for easy access to the NLP tools provided by ixaKat for Basque and IXA pipes for Spanish languages, among others.
  • Central Unit Detector for Scientific Texts: http://ixa2.si.ehu.es/clarink/tools/ES-CU-detector/detects the most salient node of a text. First, the detector segments the text in discourse units and then it labels the most important text segment.
  • SEPLN Anthology: http://scipub-taln.upf.edu/sepln/ is a Web-based information access platform which exploits the SEPLN Anthology documents to provide single-document and collection-based visualizations as a means to explore the rich generated contents.
  • PDFdigest: http://taln.upf.edu/pdfdigest is a tool for PDF-to-XML content extraction specially designed to extract scientific articles' headings and logical structure (title, authors, abstract, etc.) and its textual content. 

RESOURCES

  • GALNET:  http://sli.uvigo.gal/galnet/ is an open wordnet for Galician, aligned with the interlingual index (ILI) generated from the English WordNet3.0, following the expand model for the creation of new wordnets, where the variants associated with the Princeton WordNet synsets are translated using different strategies. Galnet can be downloaded in RDF and LMF formats from http://sli.uvigo.gal/download/SLI_Galnet/.
  • SENSOGAL: http://sli.uvigo.gal/SensoGal/ is an English-Galician parallel corpus semantically annotated with respect to WordNet 3.0 and aligned at the sentence and word level with the English SemCor corpus. The SensoGal Corpus is based on the Galician translation of the 186 fully tagged texts included in the original English Princeton SemCor
  • IULA Spanish Clinical Record Corpus: http://eines.iula.upf.edu/brat/#/NegationOnCR_IULA is a corpus of 3,194 sentences extracted from anonymized clinical records and manually annotated with negation markers and their scope.