CS918-15 Natural Language Processing

Introductory description

Knowledge of the fundamental principles of natural language processing.

Module aims

Outline syllabus

This is an indicative module outline only to give an indication of the sort of topics that may be covered. Actual sessions held may differ.

The module will address core methodologies in natural language processing and related tools and will proceed to examine current applications. The syllabus may cover:

• Regular expressions, word tokenisation, stemming, sentence segmentation
• N-grams and language models
• Part-of-Speech Tagging
• Hidden Markov Models and Maximum Entropy Models
• Semantics: Lexical Semantics, Distributional Semantics, Word Sense Disambiguation and Vector Space Models
• Text classification
• Sentiment analysis
• Information Extraction: Named Entity Recognition, Relation Extraction
• Syntactic Parsing
• Semantic Parsing
• Question Answering and Summarisation
• Recommender systems

Learning outcomes

By the end of the module, students should be able to:

• Demonstrate knowledge of the fundamental principles of natural language processing.
• Understanding of methods and algorithms used to process different types of textual data as well as the challenges involved.
• Understanding of the state of the art in the core areas of Natural Language Processing such as Language Models, Part-of-Speech tagging, Named Entity Recognition, Syntactic Parsing, Information Extraction, Text Classification, Distributional Semantics and Vector Space Models.
• Working knowledge of state of the art tools available for analysing linguistic data in the context of the above mentioned areas.
• Computational skills to create NLP processing pipelines using existing NLP libraries, retrain models and extend existing NLP tools.

Indicative reading list

Please see Talis Aspire link for most up to date list.

View reading list on Talis Aspire

Research element

Students need to do some research about features used for sentiment classifier training in Assignment 2

Subject specific skills

• Have knowledge of the fundamental principles of Natural Language Processing (NLP).
• Understanding of methods and algorithms used to process different types of textual data as well as the challenges involved.
• Understanding of the state of the art in the core areas of Natural Language Processing such as Language models, Part-Of-Speech tagging, Named Entity Recognition, Syntactic Parsing, Information Extraction, Text Classification, Distributional Semantics and Vector Space Models.
• Understanding of the state of the art in current application areas such as Semantic Parsing, Sentiment Analysis, Social Media analysis, Summarisation, Question Answering, Information Extraction.
• Working knowledge of state of the art tools available for analysing linguistic data in the context of the above mentioned areas.
• Computational skills to create NLP processing pipelines using existing NLP libraries, retrain models and extend existing NLP tools.

Transferable skills

• Analytical skills – Examine NLP problems thoroughly with attention to details
• Research skills – Identify relevant resources and background information to be used in coursework projects
• Problem solving skills – Think creatively and apply sensible approaches to solve the NLP problems given
• Communication skills – Present approaches and findings in a coherent manner in coursework reports