NLP Training
-
Session 1 - 4th Sept.-Difference between NLP and nlu | sentiment analysis | implementation of textblob | polarity | subjectivity | objectivity (109:15)
-
Session 1 - Summary
-
Session 2 -5th Sept-Implementation on dataset | data handling with pandas | textblob implementation on data (82:44)
-
Session 2 - Summary
-
Session 3 - 6th Sept-Tokenization | lemmatization | stemming | implementation of nltk (103:26)
-
Session 3 - Summary
-
Session 4 - 7th Sept-nltk installation | WordNet | Spacy | Automatic Conversion from uppercase to lowercase (113:47)
-
Session 4 - Summary
-
Session 5 - 11th Sept - Revision Session (66:16)
-
Session 6 - 12th Sept-NLU |introduction of spacy |token ID|read token|mapping| (101:52)
-
Session 7 - 18th Sept-NER | Spacy using rule based matching |Phrase Matcher |Hosting on Local Ip (95:57)
-
Session 7 - Summary
-
Session 8 - 19th Sept-Pipeline | Tokenizer |Analyze pipe using Spacy| add pipe |@language (95:46)
-
Session 8 - Summary
-
Session 9 - 20th Sept-Spacy Usage | Creating And Adding Custom Attributes| Register Token Extension (79:25)
-
Session 9 - Summary
-
Session 10 - 22nd Sept_Practice Session (49:17)
-
Session 11 - 28th Sept-use case of text classification|stemming or lemma| (96:10)
-
Session 12 - 4th Oct-text classification|TF-IDF|classification model| (102:38)
-
Session 13 - 5th Oct-TF-IDF|classify the model|write code for TF-IDF (89:55)
Extra Sessions
-
Visualization | Exploratory data analysis | One hot label encoding | Nan | Binary class | logistic regression | confusion matrix (118:54)
-
Activation function | DL | Regression | Classification | Feed forward Forward Propogation | Back propagation | Keras (267:58)
-
Binary Classification | Model using sigmoid function | Logistic regression | visuals, searborn | graph | bar graph | Discrete variable | frequency distribution table | One hot encoding | Feature Engineering | Missing value resolving using feature engineering | Imputation (123:47)
