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

Comprehensive training outline

1. Introduction to NLP
   • Concepts of NLP
   • NLP frameworks
   • Commercial use cases for NLP
   • Web data scraping
   • Utilising various APIs for text data retrieval
   • Managing text corpora: saving content and relevant metadata
   • Benefits of Python and an NLTK quick start
2. Practical Understanding of a Corpus and Dataset
   • The necessity of a corpus
   • Corpus analysis techniques
   • Categorisation of data attributes
   • File formats for corpora
   • Preparing datasets for NLP applications
3. Understanding the Structure of a Sentence
   • Core NLP components
   • Natural language understanding
   • Morphological analysis: stems, words, tokens, and speech tags
   • Syntactic analysis
   • Semantic analysis
   • Addressing ambiguity
4. Text Data Preprocessing
   • Raw text corpus
     • Sentence tokenization
     • Stemming raw text
     • Lemmatisation of raw text
     • Stop word removal
   • Raw sentence corpus
     • Word tokenization
     • Word lemmatisation
   • Constructing Term-Document and Document-Term matrices
   • Tokenizing text into n-grams and sentences
   • Customised and practical preprocessing methods
5. Analyzing Text Data
   • Fundamental NLP features
     • Parsers and parsing
     • POS tagging and taggers
     • Named entity recognition
     • N-grams
     • Bag of words
   • Statistical NLP features
     • Linear algebra concepts for NLP
     • Probabilistic theory for NLP
     • TF-IDF
     • Vectorization
     • Encoders and Decoders
     • Normalization
     • Probabilistic Models
   • Advanced feature engineering in NLP
     • Word2vec fundamentals
     • Word2vec model components
     • Logic behind the word2vec model
     • Extending the word2vec concept
     • 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 Modeling
   • Document clustering and pattern mining (including hierarchical clustering and k-means)
   • Comparing and classifying documents using TFIDF, Jaccard, and cosine distance metrics
   • Document classification using Naïve Bayes and Maximum Entropy
7. Identifying Important Text Elements
   • Dimensionality reduction: PCA, SVD, and Non-negative Matrix Factorization
   • Topic modelling and information retrieval via Latent Semantic Analysis
8. Entity Extraction, Sentiment Analysis, and Advanced Topic Modeling
   • Positive vs. negative sentiment: measuring intensity
   • Item Response Theory
   • Part-of-speech tagging applications: identifying people, places, and organizations
   • Advanced topic modelling: Latent Dirichlet Allocation
9. Case Studies
   • Extracting insights from unstructured user reviews
   • Sentiment classification and visualisation of product review data
   • Analysing search logs for usage patterns
   • Text classification
   • Topic modelling