Skip to main content

Table 10 Comparison values for Mac-Morpho v2

From: Evaluating word embeddings and a revised corpus for part-of-speech tagging in Portuguese

Model

All (%)

OOV (%)

OpenNLP MaxEnt

95.92

90.17

OpenNLP Perceptron

95.44

90.03

CharWNN [34]

97.31

93.43

WNN, Caps + suffixes [34]

97.24

92.64

  1. Best values shown in bold.