README - Data is already split into train & test Everything that contains 'train' is from training, 'test' for testing - Files *.data token-per-line format with tokens & concept tags for sequence labeling *.feats.txt POS-tag and Lemmas in token-per-line format (with tokens on first column) additional features that can be used for sequence labeling
A7ocin/LUS_concept_tagger
Language Understanding Systems midterm project: concept tagger for movie domain
Perl