lemmatizer-pl
lemmatizer-pl copied to clipboard
dzieciou
Python lemmatizer for Polish.
So that I can try and give feedback whether it is useful for entity extraction. - xces does not need to be included - I should be able to recreate...
We have Polimorf-compatible dictionary but we not have train data. Original data are for NKJP tagset. However, http://clip.ipipan.waw.pl/NationalCorpusOfPolish provides NKJP corpus reanalyzed with Polimorf tagset. That could be one training...
Experiment setup 1. Analyze chunks from PolEval 2017 and add annotations 2. Compare annotations against original PolEval 2017 annotations 3. Disambiguate with model pretrained for NKJP tagset 4. Compare disambiguated...
The goal is to have in the disambiguation pretrained model for NKJP tagset. NKJP tagset is the only tagset which I have training dataset for (from PolEval 2017). The model...
The objective is to evaluate disambiguation model for NKJP tagset. Possible experiment setup: * PolEval training set * 20 epochs * buckets of 2048 sentences (grouped by number of tokens...