Run by School of Computer Science and Electronic Engineering

20.000 Credits or 10.000 ECTS Credits

Semester 2

Organiser: Dr William Teahan

• Provide in-depth knowledge and understanding in natural language processing (NLP).
• Introduce text processing methods in Unix.
• Demonstrate how to build non-trivial NLP systems using the NLTK in Python.
• Introduce ideas and developments at the research level in natural language processing.

Indicative content includes:

• NLP programming in Python using the NLTK and text processing methods using Unix tools such as sed, awk.
• Topics in Computational Linguistics and Natural Language Processing: Zipf’s Law; Heap’s Law; the sparse data problem; the zero frequency problem; regular expressions; n-grams; language modelling; NLP pipeline e.g. tokenization -> word segmentation -> part of speech (POS) tagging -> phrase chunking -> parsing -> named entity recognition -> information extraction -> question answering.
• Topics in Information Retrieval (IR) – systems, theory and technologies: Boolean search; textual conflation e.g. stemming and stopword removal; probabilistic IR model; Vector Space IR model; relevance feedback; text categorization and information filtering; information extraction; question answering; IR systems and search engines e.g. Google’s PageRank, IBM’s Web Fountain; search engine optimization; evaluation.

excellent

Equivalent to the range 70%+. Assemble critically evaluated, relevent areas of knowledge and theory to constuct professional-level solutions to tasks and questions presented. Is able to cross-link themes and aspects to draw considered conclusions. Presents outputs in a cohesive, accurate, and efficient manner.

good

Equivalent to the range 60%-69%. Is able to analyse a task or problem to decide which aspects of theory and knowledge to apply. Solutions are of a workable quality, demonstrating understanding of underlying principles. Major themes can be linked appropriately but may not be able to extend this to individual aspects. Outputs are readily understood, with an appropriate structure but may lack sophistication.

threshold

Equivalent to 50%. Uses key areas of theory or knowledge to meet the Learning Outcomes of the module. Is able to formulate an appropriate solution to accurately solve tasks and questions. Can identify individual aspects, but lacks an awareness of links between them and the wider contexts. Outputs can be understood, but lack structure and/or coherence.

1. Separate techniques used for Computational Linguistics, Natural Language Processing, and Information Retrieval.

2. Devise a non-trivial NLP system using the NLTK in Python and Unix-based text processing.

3. Compare and contrast NLP methods and technologies and how they can be applied to constructing non-trivial systems that process natural language.

Type	Name	Description	Weight
	NLP Laboratories		40.00
	NLP Assignment		30.00
	NLP Test		30.00

		Hours
Laboratory	Practical exercises that students work through in the lab.	24
Lecture	Lectures to introduce the theory.	24
Individual Project	Assignment requiring own development and self-study.	60
Private study	Self study for the exam and to support labs.	92

• Literacy - Proficiency in reading and writing through a variety of media
• Numeracy - Proficiency in using numbers at appropriate levels of accuracy
• Computer Literacy - Proficiency in using a varied range of computer software
• Self-Management - Able to work unsupervised in an efficient, punctual and structured manner. To examine the outcomes of tasks and events, and judge levels of quality and importance
• Exploring - Able to investigate, research and consider alternatives
• Information retrieval - Able to access different and multiple sources of information
• Inter-personal - Able to question, actively listen, examine given answers and interact sensitevely with others
• Critical analysis & Problem Solving - Able to deconstruct and analyse problems or complex situations. To find solutions to problems through analyses and exploration of all possibilities using appropriate methods, rescources and creativity.
• Management - Able to utilise, coordinate and control resources (human, physical and/or financial)
• Argument - Able to put forward, debate and justify an opinion or a course of action, with an individual or in a wider group setting

• Identify emerging technologies and technology trends;
• Apply underpinning concepts and ideas of engineering;
• Apply knowledge and understanding of the specialist cognate area of computer systems engineering in an international context;
• Assess and choose optimal methods and approaches for the specification, design, implementation and evaluation of engineering solutions, especially ones that include embedded microprocessors
• Formulate and analyse requirements and practical constraints of products, processes and services, place them in an engineering context and manage their implementation;
• Solve problems logically and systematically;
• Assess and choose optimal methods and approaches for the specification, design, implementation and evaluation of engineering solutions.
• Systematically review factors affecting the implementation of a project, including safety and sustainability;
• Access and synthesize information and literature sources;
• Analyse and display data using appropriate methods and mathematical techniques;
• Demonstrate familiarity with relevant subject specific and general computer software packages.
• Demonstrate an awareness of current advances and contemporary approaches in the discipline and have strategies for keeping that awareness current;
• Demonstrate an awareness of the need to work safely and comply within relevant legislative and regulatory frameworks;
• Knowledge and understanding of facts, concepts, principles & theories
• Use of such knowledge in modelling and design
• Problem solving strategies
• Analyse if/how a system meets current and future requirements
• Deploy theory in design, implementation and evaluation of systems
• Specify, design or construct computer-based systems
• Evaluate systems in terms of quality and trade-offs
• Deploy tools effectively
• Development of general transferable skills
• Specify, deploy, verify and maintain information systems
• Defining problems, managing design process and evaluating outcomes
• System Design
• Knowledge and/or understanding of appropriate scientific and engineering principles
• Knowledge and understanding of mathematical principles
• Knowledge and understanding of computational modelling
• Specify, deploy, verify and maintain computer-based systems
• Principles of appropriate supporting engineering and scientific disciplines

Resource implications for students

Online resources are being used

Talis Reading list

http://readinglists.bangor.ac.uk/modules/ice-4721.html

Reading list

Natural Language Processing with Python

Compulsory in courses:

• Q1BC: MSc Language Technologies year 1 (MSC/LT)

Optional in courses:

• G5BB: MSc Advanced Data Science year 1 (MSC/ADS)
• G5BC: MSc Computing for Data Science year 1 (MSC/CDS)
• G5BA: MSc Computing year 1 (MSC/COMP)
• G5BD: MSc Rise of the Machines year 1 (MSC/MACH)