Applied Natural Language Processing
Offered By: Chennai Mathematical Institute via Swayam
Course Description
Overview
Natural Language Processing (NLP) is an important area of Artificial Intelligence concerned with the processing and understanding (NLU) of a human language. The goal of NLP and NLU is to process and harness information from a large corpus of text with very little manual intervention.
This course will introduce various techniques to find similar words using the context of surrounding words, build a Language model to predict the next word and generate sentences, encode every word in the vocabulary of the corpus into a vector form that represents its context and similar words and encode a sentence for machine translation and conversation purposes.
The course will help learners to gather sufficient knowledge and proficiency in probabilistic, Artificial Neural Network (ANN) and deep learning techniques for NLP.
INTENDED AUDIENCE: Any interested learners
PER-REQUISITES: Essential – Algorithms, Python proficiency, elementary probability and statistics, Linear Algebra, basic understanding of machine learning
NOTE: Only English corpus is considered throughout this course.
This course will introduce various techniques to find similar words using the context of surrounding words, build a Language model to predict the next word and generate sentences, encode every word in the vocabulary of the corpus into a vector form that represents its context and similar words and encode a sentence for machine translation and conversation purposes.
The course will help learners to gather sufficient knowledge and proficiency in probabilistic, Artificial Neural Network (ANN) and deep learning techniques for NLP.
INTENDED AUDIENCE: Any interested learners
PER-REQUISITES: Essential – Algorithms, Python proficiency, elementary probability and statistics, Linear Algebra, basic understanding of machine learning
NOTE: Only English corpus is considered throughout this course.
Syllabus
COURSE LAYOUT
WEEK 1: Introduction, terminologies, empirical rulesWEEK 2: Word to Vectors
WEEK 3: Probability and Language Model
WEEK 4: Neural Networks for NLP
WEEK 5: Distributed word vectors (word embeddings)
WEEK 6: Recurrent Neural Network, Language Model
WEEK 7: Statistical Machine Translation
WEEK 8: Statistical Machine Translation, Neural Machine Translation
WEEK 9: Neural Machine Translation
WEEK 10:Conversation Modeling, Chat-bots, dialog agents, Question Processing
WEEK 11:Information Retrieval tasks using Neural Networks- Learn to Rank, Understanding Phrases, analogiesWEEK 12:Spelling Correction using traditional and Neural networks, end notes
Taught by
Prof. Ramaseshan R
Tags
Related Courses
AWS Certified Machine Learning - Specialty (LA)A Cloud Guru Blockchain Essentials
A Cloud Guru Algorithms for DNA Sequencing
Johns Hopkins University via Coursera Applied AI with DeepLearning
IBM via Coursera Artificial Intelligence Algorithms Models and Limitations
LearnQuest via Coursera