Linguistic terminology- Morpheme, Grapheme, Phoneme, Classical Approaches of NLP,
Understanding linguistics – Morphology, Syntax, Semantics, Pragmatics. Basics of Text processing, principles
of text analysis: Regular Expression , word tokenization, Word normalization- Lemmatization and stemming,
Stop words and Key words identification, Introduction to N-Gram models, Bag of Words Representation, PoS tagging,
Statistical Approaches:
Statistical parsing, Approaches to parsing, Words & Vectors-Word 2 Vec concepts,
TF-IDF computation, Inverted Index construction , Document Incidence Matrix construction, Text similarity methods—Similarity coefficient ,Jaccard similarity, Cosine similarity
Text Classification:
Spam detection, Language Identification, Sentiment classification. Classification
Methods- supervised and unsupervised. Machine learning in action: document classification information extraction- Named Entity Recognition.
Applications of NLP:
Information retrieval in NLP, Design Feature of IR systems, Question Answering system.,
QA System types, Opinion Mining, Sentiment analysis , Recommendation system, Machine Translation, Word sense disambiguation, Word embedding concept, Duplicate detection, Concept of Shingling, Ontology construction and classification, Performance and correctness measures- Precision , Recall and f-Measure. Emerging Applications of Natural Language Generation in Information Visualization, Education, and Health
Care .
