├── LICENSE ├── README.md ├── datasets ├── README.md ├── corpora │ ├── DO_PSP │ │ ├── README.md │ │ └── dosp_29012016.csv │ ├── NER │ │ ├── README.md │ │ └── conll2003 │ │ │ ├── README.md │ │ │ ├── conll2003_test.txt │ │ │ ├── conll2003_train.txt │ │ │ └── conll2003_valid.txt │ ├── NLI │ │ ├── README.md │ │ ├── SNLI │ │ │ ├── README.md │ │ │ ├── snli_1_dev.txt │ │ │ ├── snli_1_test.txt │ │ │ └── snli_1_train.txt │ │ └── assin2 │ │ │ ├── README.md │ │ │ ├── assin2-test.xml │ │ │ ├── assin2-train-only.xml │ │ │ └── assin2-valid.xml │ ├── README.md │ ├── classification │ │ └── README.md │ ├── reuters │ │ ├── README.md │ │ ├── archive.zip │ │ └── reuters-21578.csv │ ├── test.csv │ ├── training.csv │ └── tweets_polarity_classification │ │ ├── README.md │ │ ├── SemEval2014-task3-train-valid.txt │ │ ├── SemEval2014-task3-train.txt │ │ ├── SemEval2014-task3-valid.txt │ │ ├── twitter-2013dev-A.txt │ │ ├── twitter-2013test-A.txt │ │ └── twitter-2013train-A.txt └── pdfs │ └── README.md ├── lectures ├── README.md ├── aula_named_entity_recognition.ipynb ├── aula_named_entity_recognition_crf.ipynb ├── cap01_preproc_textos.ipynb ├── cap02_representacoes_texto.ipynb ├── cap03_regex.ipynb ├── cap04_text_preprocessing.ipynb ├── cap05_1_extracao_caracteristicas.ipynb ├── cap05_extracao_caracteristicas.ipynb ├── cap06_2_cosine_similarity.ipynb ├── cap07_1_probabilistic_language_models.ipynb ├── cap08_2_metricas_avaliacao_desempenho.ipynb ├── cap08_3_estrategias_amostragem.ipynb ├── cap09_1_perceptron_simples.ipynb ├── cap09_2_multilayer_perceptron_backpropagation.ipynb ├── cap09_3_multilayer_perceptron_keras.ipynb ├── cap09_4_sentiment_analysis_dnn.ipynb ├── cap10_1_processo_anotacao.ipynb ├── cap10_2_metricas_concordancia.ipynb ├── cap11_1_basics_convolution.ipynb ├── cap11_2_cnn_alexnet.ipynb ├── cap11_3_transfer_learning.ipynb ├── cap11_4_cnn_text.ipynb ├── cap11_4_sentiment_analysis_cnn.ipynb ├── cap11_5_deep_features.ipynb ├── cap12_1_rnn.ipynb ├── cap12_2_lang_models_rnn.ipynb ├── cap13_1_embeddings_principles.ipynb ├── cap13_1_word_embeddings.py ├── cap13_2_embeddings_word2vec.ipynb ├── cap13_3_embeddings_glove.ipynb ├── cap13_4_visualization_word_embeddings.ipynb ├── cap15_2_vector_visualization.ipynb ├── cap15_3_seq2seq_machine_translation.ipynb ├── cap16_2_idmb_classification_self_attention.ipynb ├── cap17_2_idmb_classification_bert.ipynb ├── cap17_3_idmb_classification_gpt3.ipynb ├── information_retrieval_reuters.ipynb ├── natural_language_inference.ipynb └── tweet_sentiment_classification_rnn_fastai.ipynb ├── resources ├── LIWC2007_Portugues_win.dic ├── README.md ├── SentiLex-lem-PT02.txt └── cloud_classification_ccsn_ViT_kfold.ipynb └── tutorials └── ner_aula.ipynb /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/README.md -------------------------------------------------------------------------------- /datasets/README.md: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /datasets/corpora/DO_PSP/README.md: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /datasets/corpora/DO_PSP/dosp_29012016.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/datasets/corpora/DO_PSP/dosp_29012016.csv -------------------------------------------------------------------------------- /datasets/corpora/NER/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/datasets/corpora/NER/README.md -------------------------------------------------------------------------------- /datasets/corpora/NER/conll2003/README.md: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /datasets/corpora/NER/conll2003/conll2003_test.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/datasets/corpora/NER/conll2003/conll2003_test.txt -------------------------------------------------------------------------------- /datasets/corpora/NER/conll2003/conll2003_train.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/datasets/corpora/NER/conll2003/conll2003_train.txt -------------------------------------------------------------------------------- /datasets/corpora/NER/conll2003/conll2003_valid.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/datasets/corpora/NER/conll2003/conll2003_valid.txt -------------------------------------------------------------------------------- /datasets/corpora/NLI/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/datasets/corpora/NLI/README.md -------------------------------------------------------------------------------- /datasets/corpora/NLI/SNLI/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/datasets/corpora/NLI/SNLI/README.md -------------------------------------------------------------------------------- /datasets/corpora/NLI/SNLI/snli_1_dev.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/datasets/corpora/NLI/SNLI/snli_1_dev.txt -------------------------------------------------------------------------------- /datasets/corpora/NLI/SNLI/snli_1_test.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/datasets/corpora/NLI/SNLI/snli_1_test.txt -------------------------------------------------------------------------------- /datasets/corpora/NLI/SNLI/snli_1_train.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/datasets/corpora/NLI/SNLI/snli_1_train.txt -------------------------------------------------------------------------------- /datasets/corpora/NLI/assin2/README.md: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /datasets/corpora/NLI/assin2/assin2-test.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/datasets/corpora/NLI/assin2/assin2-test.xml -------------------------------------------------------------------------------- /datasets/corpora/NLI/assin2/assin2-train-only.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/datasets/corpora/NLI/assin2/assin2-train-only.xml -------------------------------------------------------------------------------- /datasets/corpora/NLI/assin2/assin2-valid.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/datasets/corpora/NLI/assin2/assin2-valid.xml -------------------------------------------------------------------------------- /datasets/corpora/README.md: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /datasets/corpora/classification/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/datasets/corpora/classification/README.md -------------------------------------------------------------------------------- /datasets/corpora/reuters/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/datasets/corpora/reuters/README.md -------------------------------------------------------------------------------- /datasets/corpora/reuters/archive.zip: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/datasets/corpora/reuters/archive.zip -------------------------------------------------------------------------------- /datasets/corpora/reuters/reuters-21578.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/datasets/corpora/reuters/reuters-21578.csv -------------------------------------------------------------------------------- /datasets/corpora/test.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/datasets/corpora/test.csv -------------------------------------------------------------------------------- /datasets/corpora/training.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/datasets/corpora/training.csv -------------------------------------------------------------------------------- /datasets/corpora/tweets_polarity_classification/README.md: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /datasets/corpora/tweets_polarity_classification/SemEval2014-task3-train-valid.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/datasets/corpora/tweets_polarity_classification/SemEval2014-task3-train-valid.txt -------------------------------------------------------------------------------- /datasets/corpora/tweets_polarity_classification/SemEval2014-task3-train.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/datasets/corpora/tweets_polarity_classification/SemEval2014-task3-train.txt -------------------------------------------------------------------------------- /datasets/corpora/tweets_polarity_classification/SemEval2014-task3-valid.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/datasets/corpora/tweets_polarity_classification/SemEval2014-task3-valid.txt -------------------------------------------------------------------------------- /datasets/corpora/tweets_polarity_classification/twitter-2013dev-A.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/datasets/corpora/tweets_polarity_classification/twitter-2013dev-A.txt -------------------------------------------------------------------------------- /datasets/corpora/tweets_polarity_classification/twitter-2013test-A.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/datasets/corpora/tweets_polarity_classification/twitter-2013test-A.txt -------------------------------------------------------------------------------- /datasets/corpora/tweets_polarity_classification/twitter-2013train-A.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/datasets/corpora/tweets_polarity_classification/twitter-2013train-A.txt -------------------------------------------------------------------------------- /datasets/pdfs/README.md: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /lectures/README.md: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /lectures/aula_named_entity_recognition.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/aula_named_entity_recognition.ipynb -------------------------------------------------------------------------------- /lectures/aula_named_entity_recognition_crf.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/aula_named_entity_recognition_crf.ipynb -------------------------------------------------------------------------------- /lectures/cap01_preproc_textos.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/cap01_preproc_textos.ipynb -------------------------------------------------------------------------------- /lectures/cap02_representacoes_texto.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/cap02_representacoes_texto.ipynb -------------------------------------------------------------------------------- /lectures/cap03_regex.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/cap03_regex.ipynb -------------------------------------------------------------------------------- /lectures/cap04_text_preprocessing.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/cap04_text_preprocessing.ipynb -------------------------------------------------------------------------------- /lectures/cap05_1_extracao_caracteristicas.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/cap05_1_extracao_caracteristicas.ipynb -------------------------------------------------------------------------------- /lectures/cap05_extracao_caracteristicas.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/cap05_extracao_caracteristicas.ipynb -------------------------------------------------------------------------------- /lectures/cap06_2_cosine_similarity.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/cap06_2_cosine_similarity.ipynb -------------------------------------------------------------------------------- /lectures/cap07_1_probabilistic_language_models.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/cap07_1_probabilistic_language_models.ipynb -------------------------------------------------------------------------------- /lectures/cap08_2_metricas_avaliacao_desempenho.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/cap08_2_metricas_avaliacao_desempenho.ipynb -------------------------------------------------------------------------------- /lectures/cap08_3_estrategias_amostragem.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/cap08_3_estrategias_amostragem.ipynb -------------------------------------------------------------------------------- /lectures/cap09_1_perceptron_simples.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/cap09_1_perceptron_simples.ipynb -------------------------------------------------------------------------------- /lectures/cap09_2_multilayer_perceptron_backpropagation.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/cap09_2_multilayer_perceptron_backpropagation.ipynb -------------------------------------------------------------------------------- /lectures/cap09_3_multilayer_perceptron_keras.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/cap09_3_multilayer_perceptron_keras.ipynb -------------------------------------------------------------------------------- /lectures/cap09_4_sentiment_analysis_dnn.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/cap09_4_sentiment_analysis_dnn.ipynb -------------------------------------------------------------------------------- /lectures/cap10_1_processo_anotacao.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/cap10_1_processo_anotacao.ipynb -------------------------------------------------------------------------------- /lectures/cap10_2_metricas_concordancia.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/cap10_2_metricas_concordancia.ipynb -------------------------------------------------------------------------------- /lectures/cap11_1_basics_convolution.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/cap11_1_basics_convolution.ipynb -------------------------------------------------------------------------------- /lectures/cap11_2_cnn_alexnet.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/cap11_2_cnn_alexnet.ipynb -------------------------------------------------------------------------------- /lectures/cap11_3_transfer_learning.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/cap11_3_transfer_learning.ipynb -------------------------------------------------------------------------------- /lectures/cap11_4_cnn_text.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/cap11_4_cnn_text.ipynb -------------------------------------------------------------------------------- /lectures/cap11_4_sentiment_analysis_cnn.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/cap11_4_sentiment_analysis_cnn.ipynb -------------------------------------------------------------------------------- /lectures/cap11_5_deep_features.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/cap11_5_deep_features.ipynb -------------------------------------------------------------------------------- /lectures/cap12_1_rnn.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/cap12_1_rnn.ipynb -------------------------------------------------------------------------------- /lectures/cap12_2_lang_models_rnn.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/cap12_2_lang_models_rnn.ipynb -------------------------------------------------------------------------------- /lectures/cap13_1_embeddings_principles.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/cap13_1_embeddings_principles.ipynb -------------------------------------------------------------------------------- /lectures/cap13_1_word_embeddings.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/cap13_1_word_embeddings.py -------------------------------------------------------------------------------- /lectures/cap13_2_embeddings_word2vec.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/cap13_2_embeddings_word2vec.ipynb -------------------------------------------------------------------------------- /lectures/cap13_3_embeddings_glove.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/cap13_3_embeddings_glove.ipynb -------------------------------------------------------------------------------- /lectures/cap13_4_visualization_word_embeddings.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/cap13_4_visualization_word_embeddings.ipynb -------------------------------------------------------------------------------- /lectures/cap15_2_vector_visualization.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/cap15_2_vector_visualization.ipynb -------------------------------------------------------------------------------- /lectures/cap15_3_seq2seq_machine_translation.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/cap15_3_seq2seq_machine_translation.ipynb -------------------------------------------------------------------------------- /lectures/cap16_2_idmb_classification_self_attention.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/cap16_2_idmb_classification_self_attention.ipynb -------------------------------------------------------------------------------- /lectures/cap17_2_idmb_classification_bert.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/cap17_2_idmb_classification_bert.ipynb -------------------------------------------------------------------------------- /lectures/cap17_3_idmb_classification_gpt3.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/cap17_3_idmb_classification_gpt3.ipynb -------------------------------------------------------------------------------- /lectures/information_retrieval_reuters.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/information_retrieval_reuters.ipynb -------------------------------------------------------------------------------- /lectures/natural_language_inference.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/natural_language_inference.ipynb -------------------------------------------------------------------------------- /lectures/tweet_sentiment_classification_rnn_fastai.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/lectures/tweet_sentiment_classification_rnn_fastai.ipynb -------------------------------------------------------------------------------- /resources/LIWC2007_Portugues_win.dic: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/resources/LIWC2007_Portugues_win.dic -------------------------------------------------------------------------------- /resources/README.md: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /resources/SentiLex-lem-PT02.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/resources/SentiLex-lem-PT02.txt -------------------------------------------------------------------------------- /resources/cloud_classification_ccsn_ViT_kfold.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/resources/cloud_classification_ccsn_ViT_kfold.ipynb -------------------------------------------------------------------------------- /tutorials/ner_aula.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/viniciusrpb/cic0269_natural_language_processing/HEAD/tutorials/ner_aula.ipynb --------------------------------------------------------------------------------