You will learn how machines can be trained to make sense of the language humans use to interact. You will come across many NLP algorithms that teach computational models about lexical processing and basic syntactic processing. You will learn the mechanism that Google Translator uses, to understand the context of language and convert to a different language. You will build a chatbot using an open-source tool, Rasa, which is a text- and voice-based conversation that understands messages, holds conversations, and connects to messaging channels and APIs. You will also learn to train the model you have created on NLU.
The machine cannot be trained to understand or process data by traditional hand-coded programs that rely heavily on very specific conditions. The moment there is a change in input, the hand-coded program is rendered useless. So, rather than having to code possible conversations, we require a model that enables the system to make sense of context.
Prior knowledge of machine learning and deep learning is beneficial; if not, we have covered all required prerequisites in the course itself.
By the end of the course, you will be able to build NLP models that can summarize blocks of text to extract the most important ideas, sentiment analysis to extract the sentiments from a given block of text and identify the type of entity extracted. All the projects included in this course are real-world projects.
All the codes and supporting files for this course are available at: https://github.com/PacktPublishing/Natural-Language-Processing-with-Rea…
Introduction to NLP, Regex, and lexical processing
Learn basic, intermediate, and advanced syntactic processing
Implement syntactic processing in a real-world project
Learn the probabilistic approach
Learn how to implement parsing in NLP
Learn about the CFG/PCFG grammar model