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

A comprehensive training roadmap

1. Foundations of NLP
   • Core concepts of NLP
   • Popular NLP Frameworks
   • Commercial uses of NLP
   • Data extraction from the web
   • Utilizing various APIs to fetch textual data
   • Managing text corpora: storing content and associated metadata
   • Benefits of using Python and an introductory NLTK session
2. Practical Insights into Corpora and Datasets
   • The necessity of a corpus
   • Analyzing corpora
   • Various data attributes
   • File formats for storing corpora
   • Dataset preparation for NLP tasks
3. Deciphering Sentence Structure
   • Key NLP components
   • Natural language understanding
   • Morphological analysis: stems, words, tokens, and speech tags
   • Syntactic analysis
   • Semantic analysis
   • Managing ambiguity
4. Preprocessing Textual Data
   • Corpus: Raw text
     • Sentence tokenization
     • Stemming raw text
     • Lemmatizing raw text
     • Eliminating stop words
   • Corpus: Raw sentences
     • Word tokenization
     • Word lemmatization
   • Managing Term-Document and Document-Term matrices
   • Tokenizing text into n-grams and sentences
   • Customized, practical preprocessing techniques
5. Text Data Analysis
   • Essential NLP features
     • Parsers and parsing techniques
     • POS tagging and taggers
     • Named entity recognition
     • N-grams
     • Bag of words approach
   • Statistical aspects of NLP
     • Linear algebra concepts for NLP
     • Probabilistic theory in NLP
     • TF-IDF methodology
     • Vectorization
     • Encoders and Decoders
     • Normalization
     • Probabilistic Models
   • Advanced Feature Engineering in NLP
     • Introduction to word2vec
     • Components of the word2vec model
     • Internal logic of word2vec
     • Extensions of word2vec concepts
     • Applying the word2vec model
   • Case Study: Bag of words application 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, k-means, and general clustering methods)
   • Comparing and classifying documents using TFIDF, Jaccard, and cosine distance metrics
   • Document classification using Naïve Bayes and Maximum Entropy
7. Identifying Key Textual Elements
   • Dimensionality reduction: Principal Component Analysis, Singular Value Decomposition, and non-negative matrix factorization
   • Topic modeling and information retrieval via Latent Semantic Analysis
8. Entity Extraction, Sentiment Analysis, and Advanced Topic Modeling
   • Distinguishing positive vs. negative sentiment
   • Item Response Theory
   • Part of speech tagging for identifying people, places, and organizations
   • Advanced topic modeling: Latent Dirichlet Allocation
9. Case Studies
   • Extracting insights from unstructured user reviews
   • Sentiment classification and visualization of product review data
   • Analyzing search logs for usage patterns
   • Text classification exercises
   • Topic modelling applications