Natural Language Processing (NLP) with Python Course

Learning Objectives:

Understand the preprocessing tasks or the computations that can be performed on natural language text. Learn about the ways to calculate word frequencies, the Maximum Likelihood Estimation (MLE) model, interpolation on data, and so on.

Topics

• Understanding word frequency
• Applying smoothing on the MLE model
• Develop a backup mechanism for MLE
• Data Interpolation
• Language modelling using metropolis hastings
• Gibbs sampling in language processing

Hands-on:

Implement Maximum Likelihood Estimation in NLTK and perform language modeling.

Learning Objectives:

Learn about stemming and lemmatization, stemmer and lemmatizer for non-English languages, developing a morphological analyzer and morphological generator using machine learning tools, search engines, and many such concepts .

Topics

• Introducing Morphology
• Understanding stemmer
• Lemmatization
• Morphological analyzer
• Morphological generator

Hands-on:

Perform preprocessing on the original text in order to implement or build an application. Implement stemming, lemmatization, and morphological analysis and generation in NLTK

Learning Objectives:

Understand the process of finding whether a character sequence, written in natural language, is in accordance with the rules defined in formal grammar. Also, learn about the process of breaking the sentences into words or phrase sequences and providing them a particular component category (noun, verb, preposition, and so on)
.

Topics

• Introducing Parsing
• Treebank construction
• Extracting Context Free Grammar (CFG) rules from Treebank
• CYK chart parsing algorithm
• Earley chart parsing algorithm

Hands-on:

Implement Context-free Grammar, Probabilistic Context-free Grammar, the CYK algorithm and the Earley algorithm.

Learning Objectives:

Understand the process of determining the meaning of character sequences or word sequences which may be used for performing the task of disambiguation.

Topics

• Introducing semantic analysis
• Named-entity recognition (NER)
• NER system using the HMM
• Training NER using machine learning toolkits
• NER using POS tagging
• Generation of the synset id from Wordnet
• Disambiguating senses using Wordnet

Learning Objectives:

Understand the process of determining the sentiments behind a character sequence. It may be used to determine whether the speaker or the person expressing the textual thoughts is in a happy or sad mood, or it represents a neutral expression.

Topics

• Introducing sentiment analysis
• Sentiment analysis using NER
• Sentiment analysis using machine learning
• Evaluation of the NER system

Learning Objectives:

Understand the process of retrieving information (for example, the number of times the word "Analysis" has appeared in the document) corresponding to a query that has been made by the user.

Topics

• Introducing information retrieval
• Stop word removal
• Information retrieval using a vector space model
• Vector space scoring and query operator interactions
• Text summarization

Hands-on:

Implement text summarization, question-answering systems, and vector space models,

Learning Objectives:

Understand the process of determining contextual information that is useful for performing other tasks, such as anaphora resolution (AR), NER, and so on.

Topics

• Introducing discourse analysis
• Discourse analysis using Centering Theory
• Anaphora resolution

Hands-on:

Use NLTK to implement first order predicate logic using UML diagrams.

Learning Objectives:

Learn to analyze whether a given NLP system produces the desired result or not and the desired performance is achieved or not which may be performed automatically using predefined metrics, or it may be performed manually by comparing human output with the output obtained by an NLP system.

Topics

• The need for the evaluation of
• NLP systems
• Evaluation of IR Systems
• Metrics for error identification
• Metrics based on lexical matching
• Metrics based on syntactic matching
• Metrics using shallow semantic matching