Natural Language Processing (NLP) - AI/Robotics Training Course

Comprehensive Training Agenda

1. Introduction to NLP
   • Foundations of NLP
   • Overview of NLP Frameworks
   • Commercial applications of NLP
   • Web data scraping techniques
   • Utilizing various APIs to fetch text data
   • Managing text corpora: storage of content and relevant metadata
   • Benefits of Python and an introductory NLTK session
2. Practical Insights into Corpora and Datasets
   • The necessity of a corpus
   • Corpus analysis methods
   • Categories of data attributes
   • File formats for corpora
   • Preparing datasets for NLP applications
3. Sentence Structure Analysis
   • Core NLP components
   • Natural language understanding
   • Morphological analysis: stems, words, tokens, and speech tags
   • Syntactic analysis
   • Semantic analysis
   • Managing ambiguity
4. Text Data Preprocessing
   • Corpus: Raw text processing
     • Sentence tokenization
     • Stemming of raw text
     • Lemmatization of raw text
     • Removal of stop words
   • Corpus: Raw sentences
     • Word tokenization
     • Word lemmatization
   • Constructing Term-Document and Document-Term matrices
   • Tokenizing text into n-grams and sentences
   • Customized preprocessing strategies
5. Text Data Analysis
   • Fundamental NLP features
     • Parsers and parsing techniques
     • Part-of-speech (POS) tagging and taggers
     • Named entity recognition
     • N-grams
     • Bag of words model
   • Statistical aspects of NLP
     • Linear algebra concepts for NLP
     • Probabilistic theory in NLP
     • TF-IDF
     • Vectorization
     • Encoders and Decoders
     • Normalization
     • Probabilistic Models
   • Advanced feature engineering in NLP
     • Introduction to word2vec
     • Components of the word2vec model
     • Underlying logic of the word2vec model
     • Extensions of the word2vec concept
     • Practical applications of the word2vec model
   • Case study: Implementing automatic text summarization using the Bag of Words approach with simplified and exact Luhn's algorithms
6. Document Clustering, Classification, and Topic Modelling
   • Document clustering and pattern mining (including hierarchical clustering and k-means)
   • Document comparison and classification using TFIDF, Jaccard, and cosine distance metrics
   • Document classification using Naïve Bayes and Maximum Entropy
7. Identifying Key Text Elements
   • Dimensionality reduction: Principal Component Analysis, Singular Value Decomposition, and Non-negative Matrix Factorization
   • Topic modelling and information retrieval via Latent Semantic Analysis
8. Entity Extraction, Sentiment Analysis, and Advanced Topic Modelling
   • Positive vs. negative: Measuring sentiment intensity
   • Item Response Theory
   • Part-of-speech tagging applications: Identifying people, places, and organizations in text
   • Advanced topic modelling: Latent Dirichlet Allocation
9. Case Studies
   • Analyzing unstructured user reviews
   • Sentiment classification and visualization of product review data
   • Mining search logs to identify usage patterns
   • Text classification
   • Topic modelling