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

Comprehensive training curriculum

1. Foundations of NLP
   • Core concepts of NLP
   • Major NLP frameworks
   • Commercial use cases for NLP
   • Web scraping for data acquisition
   • Retrieving text data via various APIs
   • Managing text corpora and preserving associated metadata
   • Benefits of Python and an NLTK quick start
2. Practical Insights into Corpora and Datasets
   • The necessity of corpora
   • Corpus examination
   • Data attribute types
   • File formats for corpora
   • Preparing datasets for NLP tasks
3. Analyzing Sentence Structure
   • Key NLP components
   • Natural language comprehension
   • Morphological analysis: stems, words, tokens, and speech tags
   • Syntactic analysis
   • Semantic analysis
   • Managing ambiguity
4. Text Data Preprocessing
   • Raw text corpora
     • Sentence segmentation
     • Stemming raw text
     • Lemmatization of raw text
     • Removal of stop words
   • Raw sentence corpora
     • Word segmentation
     • Word lemmatization
   • Handling Term-Document and Document-Term matrices
   • Tokenizing text into n-grams and sentences
   • Customized preprocessing workflows
5. Text Data Analysis
   • Essential NLP features
     • Parsers and parsing techniques
     • POS tagging and taggers
     • Named entity recognition
     • N-grams
     • Bag of words
   • Statistical aspects of NLP
     • Linear algebra concepts for NLP
     • Probability 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 word2vec
     • Extending the word2vec concept
     • Applying the word2vec model
   • Case study: Automatic text summarization using the Bag of Words approach with simplified and exact Luhn's algorithms
6. Document Clustering, Classification, and Topic Modeling
   • Document clustering and pattern mining (e.g., hierarchical clustering, k-means)
   • Document comparison and classification using TFIDF, Jaccard, and cosine similarity
   • Document classification via Naïve Bayes and Maximum Entropy
7. Extracting Significant Text Elements
   • Dimensionality reduction: PCA, SVD, and non-negative matrix factorization
   • Topic modeling and retrieval via Latent Semantic Analysis
8. Entity Extraction, Sentiment Analysis, and Advanced Topic Modeling
   • Distinguishing positive vs. negative sentiment
   • Item Response Theory
   • Applying POS tagging to identify people, places, and organizations
   • Advanced topic modeling: Latent Dirichlet Allocation
9. Case Studies
   • Analyzing unstructured user reviews
   • Sentiment classification and visualization of product reviews
   • Identifying usage patterns from search logs
   • Text classification
   • Topic modelling