Natural Language Processing (NLP) is an area of research within the field of Artificial Intelligence that has objectives that involve tasks ranging from the conversion of speech into text, to its processing and the generation of speech from it. The applications of this type of analysis are numerous: text classification, sentiment analysis or generation of automatic summaries, to name a few.
In this course -and using the Python programming language- we will review word processing techniques prior to analysis, the main text vectorization methods, and apply the analysis methodology to five fascinating and practical areas.
To attend this course attendees must know the Python programming language and have at least basic knowledge of Machine Learning.
Content:
- Introduction to NLP
- Strings in Python
- Regular expressions
- Text preprocessing
- Feature engineering
- Bag of Words
- Tf-Idf
- Word2Vec
- Document classification
- Sentiment analysis
- Supervised sentiment analysis
- Unsupervised sentiment analysis
- Text similarity
- Distances
- Recommenders
- Text summary
- Key term extraction
- Topic modeling
- Topic modeling with LSA
- Topic modeling with NMF
- Text summary
- Document clustering
