Module Details
Module Code: |
COMP9066 |
Title: |
Natural Language Processing
|
Long Title:
|
Natural Language Processing
|
NFQ Level: |
Expert |
Valid From: |
Semester 1 - 2020/21 ( September 2020 ) |
Field of Study: |
4811 - Computer Science
|
Module Description: |
Natural language processing (NLP) is a set of statistical and machine learning techniques applied to the analysis and synthesis of natural language and speech. This module will provide learners with a comprehensive introduction to the theory underpinning NLP and will also equip learners with the knowledge to implement and apply NLP algorithms and techniques to real-world problems such as sentiment analysis.
|
Learning Outcomes |
On successful completion of this module the learner will be able to: |
# |
Learning Outcome Description |
LO1 |
Apply and evaluate a language modelling technique such as n-grams to a natural language processing problem. |
LO2 |
Compare and contrast the use of parsing techniques for context-free grammar problems. |
LO3 |
Develop and evaluate a document classification model using machine learning techniques. |
LO4 |
Implement a machine translation model for real-world data and assess its performance. |
Dependencies |
Module Recommendations
This is prior learning (or a practical skill) that is strongly recommended before enrolment in this module. You may enrol in this module if you have not acquired the recommended learning but you will have considerable difficulty in passing (i.e. achieving the learning outcomes of) the module. While the prior learning is expressed as named MTU module(s) it also allows for learning (in another module or modules) which is equivalent to the learning specified in the named module(s).
|
|
Incompatible Modules
These are modules which have learning outcomes that are too similar to the learning outcomes of this module. You may not earn additional credit for the same learning and therefore you may not enrol in this module if you have successfully completed any modules in the incompatible list.
|
No incompatible modules listed |
Co-requisite Modules
|
No Co-requisite modules listed |
Requirements
This is prior learning (or a practical skill) that is mandatory before enrolment in this module is allowed. You may not enrol on this module if you have not acquired the learning specified in this section.
|
No requirements listed |
Indicative Content |
Language Modelling
Introduction to natural language processing and language models. N-gram modelling, The Markov assumption and maximum likelihood estimation. Evaluating language models, perplexity, generalization, smoothing techniques and dealing with unknown words. Hidden Markov models and part-of-speech tagging.
|
Parsing for NLP
Context free grammar. Syntactic parsing. Structural, attachment and coordination ambiguity. Handling structural ambiguities using the CKY algorithm. Statistical parsing, probabilistic context free grammars for disambiguation. Learning PCFG rule probabilities. Dependency Parsing. Dependency grammars and typed dependency structure.
|
Machine Learning
Document classification using machine learning techniques such as naive bayes (mutli-nomial and bernoulli models), support vector machines, logistic regression and neural networks (embedding dense word vectors).
|
Machine Translation (MT)
Introduction to linguistic knowledge. Rule-based MT (transfer-based MT and inter-lingual MT. Statistical MT (word and phrase-based translation). Neural MT and vector-based representations. MT evaluation metrics (WER, BLEU and TER).
|
Module Content & Assessment
|
Assessment Breakdown | % |
Coursework | 100.00% |
Assessments
No End of Module Formal Examination |
Reassessment Requirement |
Coursework Only
This module is reassessed solely on the basis of re-submitted coursework. There is no repeat written examination.
|
The University reserves the right to alter the nature and timings of assessment
Module Workload
Workload: Full Time |
Workload Type |
Contact Type |
Workload Description |
Frequency |
Average Weekly Learner Workload |
Hours |
Lecture |
Contact |
Delivers the concepts and theories underpinning the learning outcomes. |
Every Week |
2.00 |
2 |
Lab |
Contact |
Application of learning to case studies and project work. |
Every Week |
2.00 |
2 |
Independent Learning |
Non Contact |
Student undertakes independent study. The student reads recommended papers and practices implementation. |
Every Week |
3.00 |
3 |
Total Hours |
7.00 |
Total Weekly Learner Workload |
7.00 |
Total Weekly Contact Hours |
4.00 |
Workload: Part Time |
Workload Type |
Contact Type |
Workload Description |
Frequency |
Average Weekly Learner Workload |
Hours |
Lecture |
Contact |
Delivers the concepts and theories underpinning the learning outcomes. |
Every Week |
2.00 |
2 |
Lab |
Contact |
Application of learning to case studies and project work. |
Every Week |
2.00 |
2 |
Independent Learning |
Non Contact |
Student undertakes independent study. Student reads recommended papers and practices implementation. |
Every Week |
3.00 |
3 |
Total Hours |
7.00 |
Total Weekly Learner Workload |
7.00 |
Total Weekly Contact Hours |
4.00 |
Module Resources
|
Recommended Book Resources |
---|
-
N. Hardeniya J. Perkins, D. Chopra, N. Joshi, I. Mathur. (2016), Natural Language Processing: Python and NLTK, 1st. Packt Publishing, [ISBN: 9781787285101].
-
L. Hobson. H. Cole, H. Hannes. (2017), Natural Language Processing in Action: Understanding, analyzing, and generating text with Python, 1st. Manning Publications, [ISBN: 9781617294631].
| Supplementary Book Resources |
---|
-
C. Manning. (1999), Foundations of Statistical Natural Language Processing, 4th. MIT Press, [ISBN: 9780262133609].
| Recommended Article/Paper Resources |
---|
-
E. Cambria, B. White. (2014), Jumping NLP Curves: A Review of Natural
Language Processing Research, IEEE Computational Intelligence Magazine, 9,
| Supplementary Article/Paper Resources |
---|
-
J. Lafferty, A. McCallum, F. Pereira. (2001), Conditional Random Fields: Probabilistic
Models for Segmenting and Labeling
Sequence Data, International Conference on Machine
Learning,
| This module does not have any other resources |
---|
|