文件名称:NLP_Basics:自然语言处理基本概念和高级概念
文件大小:7.37MB
文件格式:ZIP
更新时间:2024-04-26 17:15:16
nlp deep-learning topic-modeling sentimentanalysis JupyterNotebook
NLP_Basics 在“ Deep_learning_for_NLP.ipynb”文件中,我尝试介绍了NLP的基础知识,并遵循了名为“自然语言处理的深度学习”的书。 我将继续更新当前的仓库。 基本的NLP模型,例如Count Vectorizer,TF-IDF,Word2Vec,嵌入,情感分析,文本分类,LSTM / BiLSTM,新的nlp库基础,主题建模等... Seq2seq建模
【文件预览】:
NLP_Basics-main
----Part 3.1: LSTM_FakeNews_Classifier.ipynb(581KB)
----Part 5.1: Topic_Modeling_using__LDA__scikit_learn.ipynb(144KB)
----Part 1.2: TF_IDF_and_Count_Vectorizer_sklearn.ipynb(16KB)
----Part 4.2: Sentiment_Analysis_Model_using_GBM_H2O.ipynb(470KB)
----Part 0.0: Deep_learning_for_NLP.ipynb(305KB)
----Dataset()
--------heart-disease-cleveland.csv(12KB)
----README.md(400B)
----deep_learning_for_nlp (1).pdf(7.21MB)
----Part 1.3: Word2Vec.ipynb(54KB)
----Part 5.2: Topic_Modeling_using_NMF_scikit_learn.ipynb(159KB)
----Part 4.1: Text_Classification_using_TFIDF_AutoML_H2O_scikit_learn.ipynb(323KB)
----Part 6.1: End_to_End_Seq2Seq_Text_Generation_Keras.ipynb(180KB)
----Part 2.1: textblob_basics.ipynb(29KB)
----Part 3.2: BidirectionalLSTM_FakeNews_Classifier.ipynb(584KB)
----Part 1.1: CountVectorizer_NaiveBayesModel_email_spam_filter.ipynb(21KB)
----Part 1.4: Word_Embeding_Keras.ipynb(17KB)