COMP53815: Natural Language Processing

• None

• None

• None

• To introduce the students to computational linguistics.
• To introduce the students to statistical and neural language models.
• To help students gain experience in using advanced techniques to solve natural language tasks such as text parsing, understanding, classification, translation, and generation.

• Text pre-processing
• Feature extraction
• Statistical language models
• Neural language models
• Neural word embeddings
• Recurrent Neural Networks (RNNs) for NLP tasks
• Advanced variations of RNNs
• Convolutional Neural Networks (CNNs) for NLP tasks
• Sequence-to-sequence architectures
• Attention and self-attention mechanisms
• Transformers
• Pretrained transformer models, e.g., BERT and GPT
• Multitask learning
• NLP ethics and fairness

Subject-specific Knowledge:

• By the end of this module, students should be able to demonstrate:
• an understanding of the fundamental concepts of language models.
• an understanding of the mathematical basis of various deep-learning-based language models.
• an understanding of the learning algorithms behind major NLP use cases e.g. machine translation, multi-task Learning, text generation and classification.
• An understanding of the embedded bias in popular language models.

Subject-specific Skills:

• By the end of this module, students should be able to demonstrate:
• an ability to conduct independent research in the field of NLP.
• an ability to handle textual data and extract representative features.
• an ability to use state-of-the-art NLP techniques and models to solve real-world tasks.

Key Skills:

• By the end of this module, students should be able to demonstrate:
• an ability to design end-to-end solutions for real-world problems with textual input using state-of-the-art NLP techniques.
• an ability to make informed decisions regarding neural architectures for NLP tasks.
• awareness of the Language Models and their biases.

• Lectures enable the students to learn new material relevant to NLP concepts, word embeddings, language models, as well as their applications.
• Computer classes enable the students to put into practice learning from lectures and strengthen their understanding through application.
• The summative assignment assesses the application of methods and techniques and assesses the understanding of core concepts. It consists of a coding exercise with accompanying report.

If you have a question about Durham's modular degree programmes, please visit our Help page. If you have a question about modular programmes that is not covered by the Help page, or a query about the on-line Postgraduate Module Handbook, please contact us.

Prospective Students: If you have a query about a specific module or degree programme, please Ask Us.

Current Students: Please contact your department.