MH6812: Advanced Natural Language Processing with Deep Learning

Course Objectives

Natural language processing (NLP) is one of the most important fields in artificial intelligence (AI). It has become very crucial in the information age because most of the information is in the form of unstructured text. NLP technologies are applied everywhere as people communicate mostly in language: language translation, web search, customer support, emails, forums, advertisement, radiology reports, to name a few.

There are several core NLP tasks and machine learning models behind NLP applications. Deep learning, a sub-field of machine learning, has recently brought a paradigm shift from traditional task-specific feature engineering to end-to-end systems and has obtained high performance across many different NLP tasks and downstream applications. Tech companies like Google, Baidu, Alibaba, Apple, Amazon, Facebook, Tencent, and Microsoft are now actively working on deep learning methods to improve their products. For example, Google recently replaced its traditional statistical machine translation and speech-recognition systems with systems based on deep learning methods.

Optional Textbooks

• Deep Learning by Goodfellow, Bengio, and Courville free online
• Machine Learning — A Probabilistic Perspective by Kevin Murphy online
• Natural Language Processing by Jacob Eisenstein free online
• Speech and Language Processing by Dan Jurafsky and James H. Martin (3rd ed. draft)

Intended Learning Outcomes

In this course, students will learn state-of-the-art deep learning methods for NLP. Through lectures and practical assignments, students will learn the necessary tricks for making their models work on practical problems. They will learn to implement and possibly invent their own deep learning models using available deep learning libraries like Pytorch.

Our Approach

• Thorough and Detailed: How to write from scratch, debug, and train deep neural models

• State of the art: Most lecture materials are new from the research world in the past 1-5 years.

• Practical: Focus on practical techniques for training the models, and on GPUs.

• Fun: Cover exciting new advancements in NLP (e.g., Transformer, ChatGPT).

Assessment Approach

Weekly Workload

• Lecture and/or tutorial and/or practical problems implemented in PyTorch.
• There will be NO office hours.

Assignments (individually graded)

• There will be two (2) assignments contributing to 2 * 25% = 50% of the total assessment.
• Students will be graded individually on the assignments. They may discuss homework assignments with each other, but they must submit individual write-ups and coding exercises.

Final Project (Group work but individually graded)

• There will be a final project contributing to the remaining 50% of the total coursework assessment.
  • 3–6 students per group
  • Presentation: 20%, report: 30%*
• The project will be group work, but the students will be graded individually. The final project presentation will ensure the student’s understanding of the project.

Course Prerequisites

• Proficiency in Python (using Numpy and PyTorch).
• Linear Algebra, basic Probability and Statistics
• Machine Learning basics

Teaching

Instructor

Luu Anh Tuan

anhtuan.luu@ntu.edu.sg

Teaching Assistants

Nguyen Tran Cong Duy

NGUYENTR003@e.ntu.edu.sg

Schedule & Course Content

Week 1: Introduction

Lecture Slide

Lecture Content

• What is Natural Language Processing?
• Why is language understanding difficult?
• What is Deep Learning?
• Deep learning vs. other machine learning methods?
• Why deep learning for NLP?
• Applications of deep learning to NLP
• Knowing the target group (background, field of study, programming experience)
• Expectation from the course

Python & PyTorch Basics

• Programming in Python

  • Jupiter Notebook and google colab
  • Introduction to Python
  • Deep Learning Frameworks
  • Why Pytorch?
  • Deep learning with PyTorch

• [Supplementary]

  • Numerical programming with Numpy/Scipy - Numpy intro
  • Numerical programming with Pytorch - Pytorch intro

Week 2: Machine Learning Basics

Lecture Slide

Lecture Content

• What is Machine Learning?
• Supervised vs. unsupervised learning
• Linear Regression
• Logistic Regression
• Multi-class classification
• Parameter estimation (MLE & MAP)
• Gradient-based optimization & SGD

Practical exercise with Pytorch

• Deep learning with PyTorch
• Linear Regressionn
• Logistic Regression
• [Supplementary]
  • Numerical programming with Pytorch - Pytorch intro

Week 3: Neural Networks & Optimization Basics

Lecture Slide

Lecture Content

• From Logistic Regression to Feed-forward NN
  • Activation functions
• SGD with Backpropagation
• Adaptive SGD (adagrad, adam, RMSProp)
• Regularization (Weight Decay, Dropout, Batch normalization, Gradient clipping)

Practical exercise with Pytorch

• Deep learning with PyTorch
• Linear Regressionn
• Logistic Regression
• Numpy notebook Pytorch notebook
  • Backpropagation
  • Dropout
  • Batch normalization
  • Initialization
  • Gradient clipping

Week 4: Word Vectors

Note: Lecture 4 will be conducted online on Sunday 7 Dec 2025, 10am via the following Zoom link:

https://ntu-sg.zoom.us/j/87693540869?pwd=9rG8wB46hI9TcqclNLk7vJvjYHlUlT.1

Meeting ID: 876 9354 0869

Passcode: 297938

Lecture Slide

Lecture Content

• Word meaning
• Denotational semantics
• Distributed representation of words
• Word2Vec models (Skip-gram, CBOW)
• Negative sampling
• FastText
• Evaluating word vectors
  • Intrinsic evaluation
  • Extrinsic evaluation
• Cross-lingual word embeddings

Practical exercise with Pytorch

Skip-gram training

Suggested Readings

• Word2Vec Tutorial - The Skip-Gram Model, blog
• Efficient Estimation of Word Representations in Vector Space - Original word2vec paper
• Distributed Representations of Words and Phrases and their Compositionality - negative sampling paper
• GloVe: Global Vectors for Word Representation
• FastText: Enriching Word Vectors with Subword Information
• Linguistic Regularities in Sparse and Explicit Word Representations.
• Neural Word Embeddings as Implicit Matrix Factorization.

Week 5: Window-based Approach and Convolutional Nets

Lecture Slide

Final Project Topic Instruction

Lecture Content

• Classification tasks in NLP
• Window-based Approach for language modeling
• Window-based Approach for NER, POS tagging, and Chunking
• Convolutional Neural Net for NLP
• Max-margin Training

Suggested Readings

• Survey on Cross-lingual embedding methods
• Slides on Cross-lingual embedding
• Adversarial autoencoder for unsupervised word translation
• Evaluating Cross-Lingual Word Embeddings
• Linear Algebraic Structure of Word Senses, with Applications to Polysemy
• Improving Distributional Similarity with Lessons Learned from Word Embeddings
• Natural Language Processing (Almost) from Scratch
• Convolutional Neural Networks for Sentence Classification
• Fast and Accurate Entity Recognition with Iterated Dilated Convolutions

Week 6: Recurrent Neural Nets

Lecture Slide

Assignment 1 is out here. Deadline: 12 Jan 2026.

Lecture Content

• Language modeling with RNNs
• Backpropagation through time
• Text generation with RNN LM
• Sequence labeling with RNNs
• Sequence classification with RNNs
• Issues with Vanilla RNNs
• Gated Recurrent Units (GRUs) and LSTMs
• Bidirectional RNNs
• Multi-layer RNNs

Practical exercise with Pytorch (CNN and RNN for NER)

• Named Entity Recognition

Suggested Readings

• N-gram Language Models
• Karpathy’s nice blog on Recurrent Neural Networks
• Building an Efficient Neural Language Model
• On the difficulty of training recurrent neural networks
• Colah’s blog on LSTMs/GRUs
• Neural Architectures for Named Entity Recognition
• Fine-grained Opinion Mining with Recurrent Neural Networks and Word Embeddings
• Zero-Resource Cross-Lingual NER
• Adaptive Softmax Paper
• Adaptive Input representation paper
• KNN-LM paper

Week 7: Machine translation and Seq2Seq Models

Lecture Slide

Lecture Content

• Machine translation
  • Early days (1950s)
  • Statistical machine translation or SMT (1990-2010)
  • Alignment in SMT
  • Decoding in SMT
  • Neural machine translation or NMT (2014 - )
• Encoder-decoder model for NMT
• Advantages and disadvantages of NMT
• Greedy vs. beam-search decoding
• MT evaluation

Suggested Readings

• Statistical Machine Translation slides, CS224n 2015 (lectures 2/3/4)
• Sequence to Sequence Learning with Neural Networks (original seq2seq NMT paper)
• Statistical Machine Translation (book by Philipp Koehn)
• A Neural Conversational Model
• BLEU (original paper)

Week 8: Seq2Seg Models, Attentions, Subwords

Note: Due to unforeseen circumstances, this week’s lecture for group A will be rescheduled to Saturday, 10 January 2026, at 6:30 pm, and will be held at NS-LT8 (together with group B). NS-LT8 (N1-02-01) is located near the Tan Chin Tuan Lecture Theatre.

Lecture Slide

Lecture Content

• Information bottleneck issue with vanilla Seq2Seq
• Attention to the rescue
• Details of attention mechanism
• Sub-word models
• Byte-pair encoding
• Hybrid models

Suggested Readings

• Neural Machine Translation by Jointly Learning to Align and Translate (original seq2seq+attention paper)
• Effective Approaches to Attention-based Neural Machine Translation
• Achieving Open Vocabulary Neural Machine Translation with Hybrid Word-Character Models

Week 9: Seq2Seq Variants and Transformer

Lecture Slide

Lecture Content

• Seq2Seq Variants (Pointer nets, Pointer Generator Nets)
  • Machine Translation
  • Summarization
• Transformer architecture
  • Self-attention
  • Positional encoding
  • Multi-head attention

The Annotated Transformer

Suggested Readings

• Get To The Point: Summarization with Pointer-Generator Networks
• Pointer Networks
• Stack-Pointer Networks for Dependency Parsing
• A Unified Linear-Time Framework for Sentence-Level Discourse Parsing
• Attention Is All You Need
• The Illustrated Transformer
• Resurrecting Submodularity in Neural Abstractive Summarization

Week 10: Self-supervised Learning & Pretrained Language Models

Assignment 2 is out here. Deadline: 17 Feb 2026, 11:59 pm.

Final project report instruction

Lecture Slide

Lecture Content

• Why semi-supervsied?

• Semisupervised learning dimensions

• Pre-training and fine-tuning methods

  • CoVe
  • TagLM
  • ELMo
  • GPT
  • ULMfit
  • BERT
  • BART

• Evaluation benchmarks

  • GLUE
  • SQuAD
  • NER
  • SuperGLUE
  • XNLI

Suggested Readings

• Cove Paper
• ULMFit paper
• BERT Paper
• ELMo paper
• BART paper

Week 11: Large Pretrained Language Models & Multilingual NLP

Lecture Slide

Lecture Content

• Large Pretrained Language Models
• Examples of Large Pretrained Language Models
• Multilingual NLP
  • Why do we need Multilingual NLP?
  • Low-resource NLP
  • Cross-lingual models
  • Multilingual models

Suggested Readings

• XLM paper
• Transformer XL paper
• XLNet paper
• mBART paper
• Pre-train Fine-tune with HF

Week 12: Bias, Robustness, Hallucination, Multimodal NLP & Recap

Lecture Slide