DSAIT4090 · Natural Language Processing MSc DSAIT · TU Delft · 2026–2027 · Period 2

Course materials

Lectures are on Thursdays. Teaching team: J. Yang (responsible), C. Lofi, A. Anand. Assessment: 20% individual assignments + 80% group project.

Schedule

Thursdays · morning 08:45 (CEG Lecture Hall E) · afternoon 13:45 (EEMCS Chip)
DateMorningAfternoonAssignment out
12 NovIntro to NLP + LogisticsYangCEG Lecture Hall E——
19 NovLexical Analysis + Language ModellingAnandCEG Lecture Hall E—A1
26 NovText Classification + EmbeddingsAnandCEG Lecture Hall ESyntax and SemanticsYangEEMCS ChipA2
3 DecDiscriminative TaskAnandCEG Lecture Hall ENeural LM & Contextual EmbeddingsYangEEMCS ChipA3
10 DecGenerative ModellingAnandCEG Lecture Hall EText Generation TasksYangEEMCS ChipA4
17 DecRetrieval-based LMsYangCEG Lecture Hall EAlignmentguestEEMCS ChipA5
7 JanInterpretabilityAnandCEG Lecture Hall EAgentsguestEEMCS Chip—
14 JanLLM ServingAnandCEG Lecture Hall ERobustnessYangEEMCS Chipfinal project due
AnandYang/ guest

Assignments

Individual · auto-graded + short reflection · laptop-runnable (no GPU required)

Group project briefs

Course-long group project (research & development) · 80% of the grade

Data & starter

Data is a public Kaggle competition; models come from HuggingFace

Join the Kaggle competition, set up API credentials, then the starter loader derives the splits:

from load_data import load_textclf, load_lm   # starter.zip
data = load_textclf()          # train / validation / test  (toxicity + identity subgroups)
train, heldout = load_lm()     # raw comment text for language-model work
# models come from HuggingFace as usual (transformers)

Content note: the comments can contain offensive language.