Course Outline
Detailed training outline
- Introduction to NLP
- Understanding NLP
- NLP Frameworks
- Commercial applications of NLP
- Scraping data from the web
- Working with various APIs to retrieve text data
- Working and storing text corpora saving content and relevant metadata
- Advantages of using Python and NLTK crash course
- Practical Understanding of a Corpus and Dataset
- Why do we need a corpus?
- Corpus Analysis
- Types of data attributes
- Different file formats for corpora
- Preparing a dataset for NLP applications
- Understanding the Structure of a Sentences
- Components of NLP
- Natural language understanding
- Morphological analysis - stem, word, token, speech tags
- Syntactic analysis
- Semantic analysis
- Handling ambigiuty
- Text data preprocessing
- Corpus- raw text
- Sentence tokenization
- Stemming for raw text
- Lemmization of raw text
- Stop word removal
- Corpus-raw sentences
- Word tokenization
- Word lemmatization
- Working with Term-Document/Document-Term matrices
- Text tokenization into n-grams and sentences
- Practical and customized preprocessing
- Corpus- raw text
- Analyzing Text data
- Basic feature of NLP
- Parsers and parsing
- POS tagging and taggers
- Name entity recognition
- N-grams
- Bag of words
- Statistical features of NLP
- Concepts of Linear algebra for NLP
- Probabilistic theory for NLP
- TF-IDF
- Vectorization
- Encoders and Decoders
- Normalization
- Probabilistic Models
- Advanced feature engineering and NLP
- Basics of word2vec
- Components of word2vec model
- Logic of the word2vec model
- Extension of the word2vec concept
- Application of word2vec model
- Case study: Application of bag of words: automatic text summarization using simplified and true Luhn's algorithms
- Basic feature of NLP
- Document Clustering, Classification and Topic Modeling
- Document clustering and pattern mining (hierarchical clustering, k-means, clustering, etc.)
- Comparing and classifying documents using TFIDF, Jaccard and cosine distance measures
- Document classifcication using Naïve Bayes and Maximum Entropy
- Identifying Important Text Elements
- Reducing dimensionality: Principal Component Analysis, Singular Value Decomposition non-negative matrix factorization
- Topic modeling and information retrieval using Latent Semantic Analysis
- Entity Extraction, Sentiment Analysis and Advanced Topic Modeling
- Positive vs. negative: degree of sentiment
- Item Response Theory
- Part of speech tagging and its application: finding people, places and organizations mentioned in text
- Advanced topic modeling: Latent Dirichlet Allocation
- Case studies
- Mining unstructured user reviews
- Sentiment classification and visualization of Product Review Data
- Mining search logs for usage patterns
- Text classification
- Topic modelling
Requirements
Knowledge and awareness of NLP principals and an appreciation of AI application in business
Testimonials
I did like the exercises.
Office for National Statistics
The trainer very easily explained difficult and advanced topics.
Leszek K
This is one of the best hands-on with exercises programming courses I have ever taken.
Laura Kahn
This is one of the best quality online training I have ever taken in my 13 year career. Keep up the great work!.
Human identification and circuit board bad point detection
王 春柱 - 中移物联网
Demonstrate
- 中移物联网
About face area.
- 中移物联网
the last day. generation part
- Accenture Inc
The topics referring to NLG. The team was able to learn something new in the end with topics that were interesting but it was only in the last day. There were also more hands on activities than slides which was good.
- Accenture Inc
I like that it focuses more on the how-to of the different text summarization methods
Organization, adhering to the proposed agenda, the trainer's vast knowledge in this subject
Ali Kattan - TWPI
the way he present everything with examples and training was so useful
Ibrahim Mohammedameen - TWPI
Very knowledgeable
Usama Adam - TWPI
This is one of the best quality online training I have ever taken in my 13 year career. Keep up the great work!.
I like that it focuses more on the how-to of the different text summarization methods