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

Comprehensive training outline

1. Introduction to NLP
   • Foundations of NLP
   • Overview of NLP frameworks
   • Commercial use cases for NLP
   • Web data scraping techniques
   • Retrieving text data via various APIs
   • Managing and storing text corpora with associated metadata
   • Benefits of Python and a rapid introduction to NLTK
2. Practical Understanding of Corpora and Datasets
   • The role of a corpus in NLP
   • Techniques for corpus analysis
   • Classification of data attributes
   • Various file formats for storing corpora
   • Dataset preparation for NLP tasks
3. Analyzing Sentence Structure
   • Core components of NLP
   • Principles of natural language understanding
   • Morphological analysis: stemming, words, tokens, and speech tags
   • Syntactic analysis methods
   • Semantic analysis approaches
   • Strategies for handling ambiguity
4. Text Data Preprocessing
   • Processing raw text corpora
     • Sentence-level tokenization
     • Stemming raw text
     • Lemmatisation of raw text
     • Removal of stop words
   • Processing raw sentence corpora
     • Word-level tokenization
     • Word lemmatisation
   • Utilising Term-Document and Document-Term matrices
   • Tokenising text into n-grams and sentences
   • Customised and practical preprocessing strategies
5. Analyzing Text Data
   • Foundational NLP features
     • Parsers and parsing techniques
     • POS tagging and tagger implementations
     • Named entity recognition
     • Handling n-grams
     • Bag of words representation
   • Statistical aspects of NLP
     • Linear algebra concepts relevant to NLP
     • Probabilistic theories in NLP
     • TF-IDF weighting
     • Vectorisation techniques
     • Encoders and decoders
     • Normalisation procedures
     • Probabilistic modelling
   • Advanced feature engineering in NLP
     • Introductory concepts of word2vec
     • Architectural components of the word2vec model
     • Underlying logic of word2vec
     • Extensions of the word2vec concept
     • Practical applications of the word2vec model
   • Case study: Applying bag of words for automatic text summarization using simplified and true Luhn's algorithms
6. Document Clustering, Classification, and Topic Modelling
   • Document clustering and pattern mining (including hierarchical and k-means clustering)
   • Comparing and classifying documents using TF-IDF, Jaccard, and cosine distance metrics
   • Document classification via Naïve Bayes and Maximum Entropy
7. Identifying Key Text Elements
   • Dimensionality reduction: PCA, 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
   • Assessing positive vs. negative sentiment intensity
   • Item Response Theory
   • POS tagging applications: identifying people, places, and organisations in text
   • Advanced topic modelling using Latent Dirichlet Allocation
9. Case Studies
   • Extracting insights from unstructured user reviews
   • Sentiment classification and visualisation of product review data
   • Mining search logs to identify usage patterns
   • Text classification projects
   • Topic modelling exercises