viterbi
- Named-Entity Recognition based on Neural Networks (22 Oct 2018)
This blog post reviews some of the recently proposed methods to perform named-entity recognition using neural networks. - Conditional Random Fields for Sequence Prediction (13 Nov 2017)
An introduction to Linear-Chain Conditional Random Fields, explaining what was the motivation behind its proposal and making a comparison with two other sequence models, Hidden-Markov Model, and Maximum Entropy Markov Model. - Maximum Entropy Markov Models and Logistic Regression (12 Nov 2017)
This blog post is an introduction to Maximum Entropy Markov Model, it points out the fundamental difference between discriminative and generative models, and what are the main advantages of the Maximum Entropy Markov Model over the Naive Bayes model. - Hidden Markov Model and Naive Bayes relationship (11 Nov 2017)
An introduction to Hidden Markov Models, one of the first proposed algorithms for sequence prediction, and its relationships with the Naive Bayes approach.
viterbi sequence-prediction scikit-learn pos-tags evaluation_metrics conditional-random-fields NER word2vec word-embeddings triplet-loss syntactic-dependencies sentence-transformers relationship-extraction neural-networks fine-tuning embeddings coursera conference classification SyntaxNet NLTK LSTM CRF wikidata transformers tokenization tf-idf text-summarisation semantic-web resources reference-post production portuguese political-science named-entity-recognition naive-bayes multi-label-classification monitoring mlops metrics maximum-entropy-markov-models logistic-regression llms language-models information-extraction imbalanced_data hyperparameter-optimization hidden-markov-models grid-search gensim generative-ai fasttext document-classification doc2vec deployment dependency-graph dataset data-challenge convolutional-neural-networks contrastive-learning books attention SPARQL RNN PyData KOVENS GRU