UNIT 016 h allocated
Text and language data
- Unicode and tokenisation
- text cleaning
- label quality
- document splits
← Course catalogue
LANGUAGE & GENERATIVE AI / CORE
NLP310Language engineering: text to transformers
24 h productive allocation9 h 36 m learning + 14 h 24 m training4 units · 1 assessed practical brief
Detailed course plan and training brief. A complete taught course pack is in preparation. The linked foundation module, where shown, is a smaller available resource.
BEFORE YOU BEGIN
A clear starting point.
Prerequisites: DL301
Core studio / CPU-friendly local or notebook environment
WHAT YOU SHOULD BE ABLE TO DEMONSTRATE
- Explain the assumptions and failure modes in text and language data.
- Complete the practical: compare a TF-IDF text classifier with a small pretrained representation and analyse failure cases without claiming language understanding from one score.
- Defend the resulting rights-cleared text corpus with reproducible evidence.
THE SUBJECTS / FOUR CONNECTED UNITS
What you will study.
UNIT 026 h allocated
Representations
- Bag-of-words
- TF-IDF
- embeddings
- semantic similarity
UNIT 036 h allocated
Attention and transformers
- Queries, keys and values
- positional information
- encoder and decoder roles
UNIT 046 h allocated
Language evaluation
- Classification and retrieval metrics
- slice analysis
- context limits
- hallucination
THE TRAINING STUDIO
Make the subject
visible in your work.
Compare a TF-IDF text classifier with a small pretrained representation and analyse failure cases without claiming language understanding from one score.
Evidence to produce
- Rights-cleared text corpus
- baseline comparison
- evaluation slices
- failure notebook
Training brief for supervised delivery. Code, datasets, answer keys and environment acceptance must be completed in the full course pack before delivery is confirmed.
ASSESS THE REASONING
A question you
should be able to answer.
When is a lexical baseline a better starting point than a large language model?
Review dimensions
Technical correctness · reproducibility · interpretation of results · failure analysis · individual explanation. Course-level rubric and faculty moderation form part of the final adopted teaching pack.
External reference access, hardware, cloud accounts and paid services are separate. No third-party certification is included by implication.