Natural Language Processing Recipes: Unlocking Text Data with Machine Learning and Deep Learning using Python - Tapa blanda

Sinopsis

Chapter 1: Extracting the data

Chapter Goal: Understanding the potential data sources to build natural language processing applications for business benefits and ways to extract the data with examples

No of pages: 20

Sub - Topics:  

1. Data extraction through API

2. Web scraping 

3. Regular expressions

4. Handling strings

Chapter 2: Exploring and processing text data

Chapter Goal: Data is never clean. This chapter will give in depth knowledge about how to clean and process the text data. It also cover tokenizing and parsing.

No of pages: 15

Sub - Topics

1. Text preprocessing methods using python

1. Data cleaning

2. Lexicon normalization

3. Tokenization 

4. Parsing and regular expressions

5. Exploratory data analysis

Chapter 3: Text to features

Chapter Goal: One of the important task with text data is to transform text data into machines or algorithms understandable form, by using different feature engineering methods 

No of pages: 20

Sub - Topics

1. Feature engineering using python

o One hot encoding

o Count vectorizer

o TF-IDF

o Word2vec

o N grams

Chapter 4: Advanced natural language processing

Chapter Goal: A comprehensive understanding of key concepts, methodologies and implementation of natural language processing techniques.

No of pages: 40

Sub - Topics: 

1. Text similarity

2. Information extraction - NER

3. Topic modeling

4. Machine learning for NLP - 

a. Text classification

b. Sentiment Analysis

5. Deep learning for NLP-

a. Seq2seq, 

b. Sequence prediction using LSTM and RNN

6. Summarizing text

Chapter 5: Industrial application with end to end implementation

Chapter Goal: Solving real time NLP applications with end to end implementation using python. Right from framing and understanding the business problem to deploying the model.

No of pages: 40

Sub - Topics:

 1.  Consumer complaint classification

 2.  Customer reviews sentiment prediction

 3.  Data stitching using text similarity and  record linkage

 4.  Text summarization for subject notes

 5.  Document clustering

  6.  Architectural details of Chatbot and Search Engine along with Learning to rank

Chapter 6: Deep learning for NLP

Chapter Goal: Unlocking the power of deep learning on text data. Solving few real-time applications of deep learning in NLP.

No of pages: 40

Sub - Topics:

1.       Fundamentals of deep learning

2.       Information retrieval using word embedding's

 3.   Text classification using deep learning approaches (CNN, RNN, LSTM, Bi-directional LSTM)

 4.   Natural language generation - prediction next word/ sequence of words using LSTM.

  5.   Text summarization using LSTM encoder and decoder.

"Sinopsis" puede pertenecer a otra edición de este libro.