RAG viterbi sequence-prediction retrieval-augmented-generation Haystack scikit-learn pos-tags evaluation_metrics conditional-random-fields classification NER word2vec word-embeddings triplet-loss syntactic-dependencies sentence-transformers relationship-extraction neural-networks fine-tuning embeddings coursera conference SyntaxNet NLTK LSTM CRF wikidata transformers tokenization tf-idf text-summarisation semantic-web semantic-drift retrieval resources reference-post production portuguese political-science named-entity-recognition naive-bayes multi-label-classification monitoring mlops metrics metadata-extraction maximum-entropy-markov-models logistic-regression llms language-models information-retrieval information-extraction imbalanced_data hyperparameter-optimization hidden-markov-models haystack grid-search gensim generative-ai fasttext evaluation document-classification doc2vec deployment dependency-graph dataset data-challenge convolutional-neural-networks contrastive-learning books attention SPARQL RNN PyData KOVENS GRU