doc2vec
- Document Classification (01 Apr 2017)
An introduction to the Document Classification task, in this case in a multi-class and multi-label scenario, proposed solutions include TF-IDF weighted vectors, an average of word2vec words-embeddings and a single vector representation of the document using doc2vec. Includes code using Pipeline and GridSearchCV classes from scikit-learn.
viterbi sequence-prediction scikit-learn pos-tags conditional-random-fields NER word2vec word-embeddings syntactic-dependencies neural-networks evaluation_metrics conference SyntaxNet NLTK LSTM CRF wikidata tokenization tf-idf resources relationship-extraction reference-post portuguese named-entity-recognition naive-bayes multi-label-classification maximum-entropy-markov-models logistic-regression language-models information-extraction imbalanced_data hyperparameter-optimization hidden-markov-models grid-search gensim fasttext embeddings document-classification doc2vec dependency-graph data-challenge convolutional-neural-networks classification books attention SPARQL RNN PyData KOVENS GRU