From 6cf651d0fd80a122f72c05b35706dfe3527f3de8 Mon Sep 17 00:00:00 2001 From: Lourens Veen Date: Wed, 30 Mar 2016 12:10:56 +0200 Subject: [PATCH] Commit for notes on _nl_conll_ner.py --- xtas/tasks/_nl_conll_ner.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/xtas/tasks/_nl_conll_ner.py b/xtas/tasks/_nl_conll_ner.py index 7c3eb06..b666132 100644 --- a/xtas/tasks/_nl_conll_ner.py +++ b/xtas/tasks/_nl_conll_ner.py @@ -31,12 +31,12 @@ def _download_training_data(): Returns an iterable over the lines of the concatenated dataset. """ - return (ln for part in ["train", "testa", "testb"] + return (ln for part in ["train", "testa", "testb"] # for ln in urlopen(_BASE_URL + part)) -def _features(sentence, i): +def _features(sentence, i): # """Baseline named-entity recognition features for i'th token in sentence. """ word = sentence[i].split()[0] @@ -70,7 +70,7 @@ def _train_ner_model(): def ner(tokens): """Baseline NER tagger for Dutch, based on the CoNLL'02 dataset.""" - +# global _model X = [_features(tokens, i) for i in range(len(tokens))]