PAMPO - Extract Named Entities from texts

Documentation Status Updates

Package to extract named entities from texts written in Portuguese and potentially applicable to other languages

Features

  • Extract entities from Portuguese texts.

TODO

  • Classify entity by category (Person, Organization, Location, etc)
  • Support accentuation

Credits

Citation

If you use this library in academy please cite our paper:

@ARTICLE{2016arXiv161209535R,
   author = {{Rocha}, C. and {Jorge}, A. and {Sionara}, R. and {Brito}, P. and
        {Pimenta}, C. and {Rezende}, S.},
    title = "{PAMPO: using pattern matching and pos-tagging for effective Named Entities recognition in Portuguese}",
  journal = {ArXiv e-prints},
archivePrefix = "arXiv",
   eprint = {1612.09535},
 primaryClass = "cs.IR",
 keywords = {Computer Science - Information Retrieval, Computer Science - Computation and Language},
     year = 2016,
    month = dec,
   adsurl = {http://adsabs.harvard.edu/abs/2016arXiv161209535R},
  adsnote = {Provided by the SAO/NASA Astrophysics Data System}
}