Relations extracted from a Portuguese dictionary: results and first evaluation



This paper presents PAPEL, a lexical resource for Portuguese, consisting of relations between terms, extracted by (semi) automatic means from a general language dictionary. An overview on the construction process is given, the included relations are presented and a quantitative vision is provided together with some examples. Synonymy relations were evaluated using a thesaurus as a golden standard and the other relations were rendered to natural language patterns and searched for in a corpus. The results of the evaluation are shown and discussed.


information extraction, dictionaries, semantic relations


Natural Language Processing

Related Project

PAPEL - Palavras Associadas Porto Editora Linguateca


14th Portuguese Conference on Artificial Intelligence (EPIA 2009), Aveiro, Portugal, October 2009

Cited by

Year 2015 : 2 citations

 Granada, R. L. (2015). Evaluation of methods for taxonomic relation extraction from text. PhD thesis, Pontifical Catholic University of Rio Grande do Sul.

 de Sousa, H. T. (2015). Caracterização de um corpus jornalístico português. Master’s thesis, Universidade do Porto.

Year 2014 : 1 citations

 Valeria De Paiva, Livy Real, Alexandre Rademaker and Gerard De Melo. NomLex-PT: A Lexicon of Portuguese Nominalizations. Proceedings of the 9th International Conference on Language Resources and Evaluation (LREC'14), Reykjavik, Iceland, ELRA, May 2014.

Year 2010 : 2 citations

 A Quantitative Approach to Concept Analysis, Rogelio Nazar, PhD thesis, Universitat Pompeu Fabra, 2010

 Hernani Pereira Costa. Automatic Extraction and Validation of Lexical Ontologies from text. MSc Thesis. University of Coimbra, 2010