Chapter 1: Natural Language Basics
Chapter Goal: Introduces the readers to the basics of NLP and Text processing
No of pages: 40 - 50
Sub -Topics
1. Language Syntax and Structure
2. Text formats and grammars
3. Lexical and Text Corpora resources
4. Deep dive into the Wordnet corpus
5. Parts of speech, Stemming and lemmatization
Chapter 2: Python for Natural Language Processing
Chapter Goal: A useful chapter for people focusing on how to setup your own python environment for NLP and also some basics on handling text data with python and coverage of popular open source frameworks for NLP
No of pages: 20 - 30
Sub - Topics
1. Setup Python for NLP
2. Handling strings with Python
3. Regular Expressions with Python
4. Quick glance into nltk, gensim, spacy, scikit-learn, keras
Chapter 3: Processing and Understanding Text
Chapter Goal: This chapter covers all the techniques and capabilities needed for processing and parsing text into easy to understand formats. We also look at how to segment and normalize text.
No of pages : 35 - 40
Sub - Topics:
1. Sentence and word tokenization
2. Text tagging and chunking
3. Text Parse Trees
3. Text normalization
4. Text spell checks and removal of redundant characters
5. Synonyms and Synsets
Chapter 4: Feature Engineering for Text Data
Chapter Goal: This chapter covers important strategies to extract meaningful features from unstructured text data. This includes traditional techniques as well as newer deep learning based methods.
No of pages : 40 - 50
Sub - Topics:
1. Feature engineering strategies for text data
2. Bag of words model
3. TF-IDF model
3. Bag of N-grams model
4. Topic Models
5. Word Embedding based models (word2vec, glove)
Chapter 5: Text Classification
Chapter Goal: Introduces readers to the concept of classification as a supervised machine learning problem and looks at a real world example for classifying text documents
No of pages: 30 - 40
Sub - Topics:
1. Classification basics
2. Types of classifiers
3. Feature generation of text documents
4. Binary and multi-class classification models
5. Building a text classifier on real world data with machine learning
6. Some coverage of deep learning based classifiers
7. Evaluating Classifiers
Chapter 6: Text summarization and topic modeling
Chapter Goal: Introduces the concepts of text summarization, n-gram tagging analysis and topic models to the readers and looks at some real world datasets and hands-on implementations on the same
No of pages: 40 - 45
Sub - Topics:
1. Text summarization concepts
2. Dimensionality reduction
3. N-gram tagging models
4. Topic modeling using LDA and LSA
5. Generate topics from real world data
6. N-gram analysis to generate patterns from app reviews (only if it performs well)
7. Basics on deep learning for summarization
Chapter 7: Text Clustering and Similarity analysis
Chapter Goal: We look at unsupervised machine learning concepts here like text clustering and similarity measures
No of pages: 35 - 40
Sub - Topics:
1. Clustering concepts
2. Analyzing text similarity
3. Implementing text similarity with cosine, jaccard meas
