Natural Language Processing Lecture
Introduction
1. Access and Preprocess Text
1.1. Access and Analyse Contents of Textfiles
1.2. Access Contents of HTML Page
1.3. Download HTML Files
1.4. Access RSS Feed
1.5. Regular expressions in Python
1.6. Access Tweets
2. Word Normalisation
2.1. Morphology
2.2. TextBlob Stemming and Lemmatization
2.3. Correction of Spelling Errors
3. Part-Of-Speech Tagging
3.1. PoS Tagsets
3.3. POS Tagging with NLTK
4. N-Gram Language Model
5. Vector Representations of Words and Documents
5.1. Vector Space Model
5.3. Implementation of BoWs
5.4. Implementation of Word-Embeddings
6. Topic Extraction
6.1. Latent Semantic Indexing (LSI)
6.2. Implementation of Topic Extraction and Document Clustering
7. Text Classification
7.1. Validation of Classifiers
7.2. Naive Bayes Text Classification
7.3. Text Classification Application: Fake News detection
8. Neural Networks
8.1. Neural Networks Introduction
8.2. Recurrent Neural Networks
8.3. Convolutional Neural Networks
8.4. CNN, LSTM and Attention for IMDB Movie Review classification
8.5. Sequence-To-Sequence, Attention, Transformer
9. References
Index