Automatic extraction and evaluation of MWE

Zilio, Leonardo;Svoboda, Luiz;Rossi, Luiz Henrique Longhi;Feitosa, Rafael Martins
(2011) Proceedings of the 8th Brazilian Symposium in Information and Human Language Technology — 214-218, published

Files

2011 - STIL - Automatic extraction and evaluation of MWE.pdf
  • Open Access
  • Adobe PDF
  • 265.27 KB
Download

Details

Authors
  • Zilio, LeonardoUCLouvain
    Author
  • Svoboda, LuizUFRGS
    Author
  • Rossi, Luiz Henrique LonghiUFRGS
    Author
  • Feitosa, Rafael MartinsUFRGS
    Author
Abstract
(en) This short paper aims at presenting a method for automatically extracting and evaluating MWE in the Europarl corpus. For this purpose we make use of mwetoolkit and utilize its output to find rules for the automatic evaluation of MWE. We then developed an XML parser to evaluate MWE candidates against those rules and also against online dictionaries. A sample of the results was manually evaluated by linguists and we had 87% of precision.
Affiliations

Citations

  • APA
  • Chicago
  • FWB

Zilio, L., Svoboda, L., Rossi, L. H. L., & Feitosa, R. M. (2011). Automatic extraction and evaluation of MWE. In Helena de Medeiros Caseli, Lucia Specia (ed.), Proceedings of the 8th Brazilian Symposium in Information and Human Language Technology (pp. 214-218). Sociedade Brasileira de Computação. https://hdl.handle.net/2078.5/277115