viterbi sequence-prediction pos-tags scikit-learn conditional-random-fields NER syntactic-dependencies evaluation_metrics document-classification classification SyntaxNet NLTK word2vec tokenization tf-idf stanford-NER relationship-extraction neural-networks named-entity-recognition naive-bayes multi-label-classification maximum-entropy-markov-models logistic-regression information-extraction imbalanced_data hyperparameter-optimization hidden-markov-models grid-search gensim doc2vec dependency-graph deep-learning convolutional-neural-networks PyData LSTM