Natural Language Processing

(CSCI-SHU 376)

Fall 2026 | New York University Shanghai

Hua Shen

Instructor

Hua Shen

Time Mon/Wed 11:15 AM - 12:30 PM
Location S311
Welcome! 🤗
Natural language processing (NLP), a form of artificial intelligence (AI) that gives computers the ability to read, understand and interpret human languages, is one of the most important technologies that have made significant progress recently. NLP has been applied to many areas such as machine translation, question answering, summarization, dialogue etc. The course will introduce students to the basics of NLP, including standard frameworks as well as algorithms and techniques to solve NLP problems, including recent deep learning approaches.

Overview
Office Hour
Hua Shen: 2:30 PM - 4:30 PM, Friday (or by appointment);
Office: S749; Zoom: https://nyu.zoom.us/my/hua.shen (Passcode: enQb9h)
Prerequisite:
Required: Machine Learning, Calculus, Probability and Statistics;
Desirable/Helpful: Linear Algebra, Data Structures, Pytorch
Class Schedule
See NYU Shanghai's Course Syllabus for the tentative schedule, which is subject to change.
Date Theme Topics Reading Materials
1
Aug 31 (Mon)
Introduction: NLP Landscape and History, Course Objectives
Lecture 1 Team Registration
1
Sep 2 (Wed) Theme 1: Statistical and Feature-Based NLP
N-gram LMs
Lecture 2
2
Sep 7 (Mon) Theme 1: Statistical and Feature-Based NLP
Text classification & log-linear models
Lecture 3
2
Sep 9 (Wed) Theme 2: Neural NLP
Word Embeddings, Pytorch
🎓 Quiz 1 🎓 HW1 Out
3
Sep 14 (Mon) Theme 2: Neural NLP
Neural Networks
3
Sep 16 (Wed) Theme 2: Neural NLP
RNN & LSTM
🎓 Quiz 2 🎓 Project Proposal Due
4
Sep 21 (Mon) Theme 2: Neural NLP
Machine Translation (Seq2Seq Models)
4
Sep 23 (Wed) Theme 3: Transformers & Pretraining
Transformers
🎓 Quiz 3 Lecture 7
5
Sep 28 (Mon) Theme 3: Transformers & Pretraining
Contextualized representations and LM-pretraining
5
Sep 30 (Wed) Theme 4: Foundation Models / LLMs
LLM Pretraining and Instruction Finetuning
🎓 Quiz 4 Lecture 10
6
Oct 12 (Mon) Theme 4: Foundation Models / LLMs
LLM in-context Learning and RLHF
🎓 HW1 Due Lecture 11
6
Oct 14 (Wed) Theme 4: Foundation Models / LLMs
LLM Decoding
🎓 HW2 Out Lecture 12
7
Oct 19 (Mon)
NO CLASS, Mid-Term Preparation
7
Oct 21 (Wed)
NO CLASS, Mid-Term Preparation
8
Oct 26 (Mon) MIDTERM 🎓 Midterm Exam
8
Oct 28 (Wed)
NO CLASS, Meet Hua about Project Progress
9
Nov 2 (Mon) Theme 5: Agentic LLMs
LLM Agents
🎓 Quiz 5 Lecture 16
9
Nov 4 (Wed) Theme 5: Agentic LLMs
Multi-Agent Systems
🎓 HW2 Due 🎓 HW3 Out Lecture 17
10
Nov 9 (Mon)
🎓 Mid-Project Presentation I
Lecture 15
10
Nov 11 (Wed)
🎓 Mid-Project Presentation II
11
Nov 16 (Mon)
NO CLASS, Meet Hua about Final Projects
11
Nov 18 (Wed) Theme 6: Open Research Directions of LLMs
Value Alignment of LLM
🎓 Quiz 6
12
Nov 23 (Mon) Theme 6: Open Research Directions of LLMs
Retrieval-augmented LLM
Lecture 16
12
Nov 25 (Wed) Theme 6: Open Research Directions of LLMs
LLM Reasoning
🎓 HW3 Due Lecture 17
13
Nov 30 (Mon) Theme 7: LLM Interpretability
Mechanistic Interpretability Approaches
Lecture 18
13
Dec 2 (Wed) Theme 7: LLM Interpretability
Human Evaluation and Interactive Explanation
Lecture 19
14
Dec 7 (Mon) Theme 8: Speech Processing
Speech Language Models
🎓 Quiz 7 Lecture 19
14
Dec 9 (Wed)
NO CLASS, Meet Hua about Final Projects
🎓 Project Due
15
Dec 14 (Mon)
🎓 Final-Project Presentation I
Lecture 18
15
Dec 16 (Wed)
🎓 Final-Project Presentation II
Lecture 19