Natural language processing (NLP) is a crucial part of artificial intelligence (AI), modeling how people share information. In recent years, deep learning approaches have obtained very high performance on many NLP tasks. In this course, students gain a thorough introduction to cutting-edge neural networks for NLP.

Content

What is this course about?

Natural language processing (NLP) or computational linguistics is one of the most important technologies of the information age. Applications of NLP are everywhere because people communicate almost everything in language: web search, advertising, emails, customer service, language translation, virtual agents, medical reports, politics, etc. In the 2010s, deep learning (or neural network) approaches obtained very high performance across many different NLP tasks, using single end-to-end neural models that did not require traditional, task-specific feature engineering. In the 2020s amazing further progress was made through the scaling of Large Language Models, such as ChatGPT. In this course, students will gain a thorough introduction to both the basics of Deep Learning for NLP and the latest cutting-edge research on Large Language Models (LLMs). Through lectures, assignments and a final project, students will learn the necessary skills to design, implement, and understand their own neural network models, using the Pytorch framework.

“Take it. CS221 taught me algorithms. CS229 taught me math. CS224N taught me how to write machine learning models.” – A CS224N student on Carta

Previous offerings

Below you can find archived websites and student project reports from previous years. Disclaimer: assignments change from year to year; please do not do assignments from previous years!

Prerequisites

• Proficiency in Python

All class assignments will be in Python (using NumPy and PyTorch). If you need to remind yourself of Python, or you’re not very familiar with NumPy, you can come to the Python review session in week 1 (listed in the schedule). If you have a lot of programming experience but in a different language (e.g. C/C++/Matlab/Java/Javascript), you will probably be fine.

• College Calculus, Linear Algebra (e.g. MATH 51, CME 100)

You should be comfortable taking (multivariable) derivatives and understanding matrix/vector notation and operations.

• Basic Probability and Statistics (e.g. CS 109 or equivalent)

You should know the basics of probabilities, gaussian distributions, mean, standard deviation, etc.

• Foundations of Machine Learning (e.g. CS221, CS229, CS230, or CS124)

We will be formulating cost functions, taking derivatives and performing optimization with gradient descent. If you already have basic machine learning and/or deep learning knowledge, the course will be easier; however it is possible to take CS224N without it. There are many introductions to ML, in webpage, book, and video form. One approachable introduction is Hal Daumé’s in-progress A Course in Machine Learning. Reading the first 5 chapters of that book would be good background. Knowing the first 7 chapters would be even better!

Reference Texts

The following texts are useful, but none are required. All of them can be read free online.

• Dan Jurafsky and James H. Martin. Speech and Language Processing (2024 pre-release)
• Jacob Eisenstein. Natural Language Processing
• Yoav Goldberg. A Primer on Neural Network Models for Natural Language Processing
• Ian Goodfellow, Yoshua Bengio, and Aaron Courville. Deep Learning
• Delip Rao and Brian McMahan. Natural Language Processing with PyTorch (requires Stanford login).
• Lewis Tunstall, Leandro von Werra, and Thomas Wolf. Natural Language Processing with Transformers

If you have no background in neural networks but would like to take the course anyway, you might well find one of these books helpful to give you more background:

• Michael A. Nielsen. Neural Networks and Deep Learning
• Eugene Charniak. Introduction to Deep Learning

Coursework

Assignments (48%)

There are four weekly assignments, which will improve both your theoretical understanding and your practical skills. All assignments contain both written questions and programming parts. In office hours, TAs may look at students’ code for assignments 1 and 2, but not for assignments 3 and 4.

• Credit:

• Assignment 1 (6%): Introduction to word vectors

• Assignment 2 (14%): Neural network foundations, calculating tensor derivatives, dependency parsing

• Assignment 3 (14%): Neural Machine Translation with sequence-to-sequence, attention, and subwords

• Assignment 4 (14%): Self-supervised learning and fine-tuning with Transformers

• Deadlines: All assignments are due on either a Tuesday or a Thursday before class (i.e. before 4:30pm). All deadlines are listed in the schedule.

• Submission: Assignments are submitted via Gradescope. You will be able to access the course Gradescope page on Canvas. If you need to sign up for a Gradescope account, please use your @stanford.edu email address. Further instructions are given in each assignment handout. Do not email us your assignments.

• Late start: If the result gives you a higher grade, we will not use your assignment 1 score, and we will give you an assignment grade based on counting each of assignments 2–4 at 16%.

• Collaboration: Study groups are allowed, but students must understand and complete their own assignments, and hand in one assignment per student. If you worked in a group, please put the names of the members of your study group at the top of your assignment. Please ask if you have any questions about the collaboration policy.

• Honor Code: We expect students to not look at solutions or implementations online. Like all other classes at Stanford, we take the student Honor Code seriously. We sometimes use automated methods to detect overly similar assignment solutions.

Final Project (49%)

The Final Project offers you the chance to apply your newly acquired skills towards an in-depth application. Students have two options: the Default Final Project (in which students tackle a predefined task, namely implementing a minimalist version of BERT) or a Custom Final Project (in which students choose their own project involving human language and deep learning). Examples of both can be seen on last year’s website. Note: TAs may not look at students’ code for either the default or custom final projects.

Important information

• Credit: For both default and custom projects, credit for the final project is broken down as follows:

• Project proposal (8%)

• Project milestone (6%)

• Project poster (3%)

• Project report (32%)

• Deadlines: The project proposal, milestone and report are all due at 4:30pm. All deadlines are listed in the schedule.

• Default Final Project: In this project, students implement parts of the BERT architecture and use it to tackle 3 downstream tasks. Similar to previous years, the code is in PyTorch.

• Project advice [lecture slides] [custom project tips]: The Practical Tips for Final Projects lecture provides guidance for choosing and planning your project. To get project advice from staff members, first look at each staff member’s areas of expertise on the office hours page. This should help you find a staff member who is knowledgable about your project area.

• Ethics-related questions: For guidance on projects dealing with ethical questions, or ethical questions that arise during your project, please contact Benji Xie (benjixie@stanford.edu) or Regina Wang (reginalw@stanford.edu).

Practicalities

• Team size: Students may do final projects solo, or in teams of up to 3 people. We strongly recommend you do the final project in a team. Larger teams are expected to do correspondingly larger projects, and you should only form a 3-person team if you are planning to do an ambitious project where every team member will have a significant contribution.

• Contribution: In the final report we ask for a statement of what each team member contributed to the project. Team members will typically get the same grade, but we may differentiate in extreme cases of unequal contribution. You can contact us in confidence in the event of unequal contribution.

• External collaborators: You can work on a project that has external (non CS224N student) collaborators, but you must make it clear in your final report which parts of the project were your work.

• Sharing projects: You can share a single project between CS224N and another class, but we expect the project to be accordingly bigger, and you must declare that you are sharing the project in your project proposal.

• Mentors: Every custom project team has a mentor, who gives feedback and advice during the project. Default project teams do not have mentors. A project may have an external (i.e., not course staff) mentor; otherwise, we will assign a CS224N staff mentor to custom project teams after project proposals.

• Computing resources: All teams will receive credits to use Google Cloud Platform, thanks to a kind donation by Google!

• Using external resources: The following guidelines apply to all projects (though the default project has some more specific rules, details provided in the Honor Code section of the handout):

• You can use any deep learning framework you like (PyTorch, TensorFlow, etc.)

• More generally, you may use any existing code, libraries, etc. and consult any papers, books, online references, etc. for your project. However, you must cite your sources in your writeup and clearly indicate which parts of the project are your contribution and which parts were implemented by others.

• Under no circumstances may you look at another CS224N group’s code, or incorporate their code into your project.

Participation (3%)

We appreciate everyone being actively involved in the class! There are several ways of earning participation credit, which is capped at 3%:

• Attending guest speakers’ lectures:

• In the second half of the class, we have two invited speakers. Our guest speakers make a significant effort to come lecture for us, so (both to show our appreciation and to continue attracting interesting speakers) we do not want them lecturing to a largely empty room. As such, we encourage students to attend these virtual lectures live, and participate in Q&A.

• All students get 0.75% per speaker (1.5% total) for either attending the guest lecture in person, or by writing a reaction paragraph if you watched the talk remotely; details will be provided. Students do not need to attend lecture live to write these reaction paragraphs; they may watch asynchronously.

• Completing feedback surveys: We will send out two feedback surveys (mid-quarter and end-of-quarter) to help us understand how the course is going, and how we can improve. Each of the two surveys are worth 0.5%.

• Ed participation: The top ~20 contributors to Ed will get 3%; others will get credit in proportion to the participation of the ~20th person.

• Karma point: Any other act that improves the class, like helping out another student in office hours or writing a useful guide for students on some topic, which a CS224N TA or instructor notices and deems worthy: 1%

Late Days

• Each student has 6 late days to use. A late day extends the deadline 24 hours. You can use up to 3 late days per assignment (including all four assignments, project proposal, project milestone and project final report).
• Final project teams can share late days between members. For example, a group of three people must have at least six late days between them to extend the deadline by two days. If any late days are being shared, this must be clearly marked at the beginning of the report, and we will release a form on Ed that teams should fill out..
• Once you have used all 6 late days, the penalty is 1% off the final course grade for each additional late day.

Regrade Requests

If you feel you deserved a better grade on an assignment, you may submit a regrade request on Gradescope within 3 days after the grades are released. Your request should briefly summarize why you feel the original grade was unfair. Your TA will reevaluate your assignment as soon as possible, and then issue a decision. If you are still not happy, you can ask for your assignment to be regraded by an instructor.

Credit/No credit enrollment

If you take the class credit/no credit then you are graded in the same way as those registered for a letter grade. The only difference is that, providing you reach a C- standard in your work, it will simply be graded as CR.

All students welcome

We are committed to doing what we can to work for equity and to create an inclusive learning environment that actively values the diversity of backgrounds, identities, and experiences of everyone in CS224N. We also know that we will sometimes make missteps. If you notice some way that we could do better, we hope that you will let someone in the course staff know about it.

Well-Being and Mental Health

If you are experiencing personal, academic, or relationship problems and would like to talk to someone with training and experience, reach out to the Counseling and Psychological Services (CAPS) on campus. CAPS is the university’s counseling center dedicated to student mental health and wellbeing. Phone assessment appointments can be made at CAPS by calling 650-723-3785, or by accessing the VadenPatient portal through the Vaden website.

Auditing the course

In general we are happy to have auditors if they are a member of the Stanford community (registered student, official visitor, staff, or faculty). If you want to actually master the material of the class, we very strongly recommend that auditors do all the assignments. However, due to high enrollment, we cannot grade the work of any students who are not officially enrolled in the class.

Students with Documented Disabilities

We assume that all of us learn in different ways, and that the organization of the course must accommodate each student differently. We are committed to ensuring the full participation of all enrolled students in this class. If you need an academic accommodation based on a disability, you should initiate the request with the Office of Accessible Education (OAE). The OAE will evaluate the request, recommend accommodations, and prepare a letter for faculty. Students should contact the OAE as soon as possible and at any rate in advance of assignment deadlines, since timely notice is needed to coordinate accommodations. Students should also send your accommodation letter to either the staff mailing list (cs224n-spr2324-staff@lists.stanford.edu) or make a private post on Ed, as soon as possible.

**OAE accommodations for group projects: ** OAE accommodations will not be extended to collaborative assignments.

AI Tools Policy

Students are required to independently submit their solutions for CS224N homework assignments. Collaboration with generative AI tools such as Co-Pilot and ChatGPT is allowed, treating them as collaborators in the problem-solving process. However, the direct solicitation of answers or copying solutions, whether from peers or external sources, is strictly prohibited.

Employing AI tools to substantially complete assignments or exams will be considered a violation of the Honor Code. For additional details, please refer to the Generative AI Policy Guidance here.

Sexual violence

Academic accommodations are available for students who have experienced or are recovering from sexual violence. If you would like to talk to a confidential resource, you can schedule a meeting with the Confidential Support Team or call their 24/7 hotline at: 650-725-9955. Counseling and Psychological Services also offers confidential counseling services. Non-confidential resources include the Title IX Office, for investigation and accommodations, and the SARA Office, for healing programs. Students can also speak directly with the teaching staff to arrange accommodations. Note that university employees – including professors and TAs – are required to report what they know about incidents of sexual or relationship violence, stalking and sexual harassment to the Title IX Office. Students can learn more at [https://vaden.stanford.edu/sexual-assault](https://web.stanford.edu/class/archive/cs/cs224n/are recovering from).

Schedule

Updated lecture slides will be posted here shortly before each lecture. Other links contain last year’s slides, which are mostly similar.

Lecture notes will be uploaded a few days after most lectures. The notes (which cover approximately the first half of the course content) give supplementary detail beyond the lectures.

Disclaimer: Assignments change; please do not do old assignments. We will give no points for doing last year’s assignments.

Date Description Course Materials Events Deadlines Week 1

Tue Apr 2

Word Vectors [slides] [notes] Suggested Readings:

1. Efficient Estimation of Word Representations in Vector Space (original word2vec paper)

2. Distributed Representations of Words and Phrases and their Compositionality (negative sampling paper) Assignment 1 out [code] [preview] Thu Apr 4 Word Vectors and Language Models [slides] [notes] [code] Suggested Readings:

3. GloVe: Global Vectors for Word Representation (original GloVe paper)

4. Improving Distributional Similarity with Lessons Learned from Word Embeddings

5. Evaluation methods for unsupervised word embeddings Additional Readings:

6. A Latent Variable Model Approach to PMI-based Word Embeddings

7. Linear Algebraic Structure of Word Senses, with Applications to Polysemy

8. On the Dimensionality of Word Embedding

Fri Apr 5 Python Review Session [slides] [colab] ** 3:30pm - 4:20pm Gates B01 Week 2

Tue Apr 9

Backpropagation and Neural Network Basics [slides] [notes] Suggested Readings:

1. matrix calculus notes

2. Review of differential calculus

3. CS231n notes on network architectures

4. CS231n notes on backprop

5. Derivatives, Backpropagation, and Vectorization

6. Learning Representations by Backpropagating Errors (seminal Rumelhart et al. backpropagation paper) Additional Readings:

7. Yes you should understand backprop

8. Natural Language Processing (Almost) from Scratch Assignment 2 out [code] [handout] [latex template] Assignment 1 due Thu Apr 11 Dependency Parsing [slides] [notes] Suggested Readings:

9. Incrementality in Deterministic Dependency Parsing

10. A Fast and Accurate Dependency Parser using Neural Networks

11. Dependency Parsing

12. Globally Normalized Transition-Based Neural Networks

13. Universal Stanford Dependencies: A cross-linguistic typology

14. Universal Dependencies website

15. Jurafsky & Martin Chapter 18

Fri Apr 12 PyTorch Tutorial Session [colab] * * 3:30pm - 4:20pm Gates B01 Week 3

Tue Apr 16

Recurrent Neural Networks [slides] [notes (lectures 5 and 6)] Suggested Readings:

1. N-gram Language Models (textbook chapter)
2. The Unreasonable Effectiveness of Recurrent Neural Networks (blog post overview)
3. Sequence Modeling: Recurrent and Recursive Neural Nets (Sections 10.1 and 10.2)
4. On Chomsky and the Two Cultures of Statistical Learning
5. Sequence Modeling: Recurrent and Recursive Neural Nets (Sections 10.3, 10.5, 10.7-10.12)
6. Learning long-term dependencies with gradient descent is difficult (one of the original vanishing gradient papers)
7. On the difficulty of training Recurrent Neural Networks (proof of vanishing gradient problem)
8. Vanishing Gradients Jupyter Notebook (demo for feedforward networks)
9. Understanding LSTM Networks (blog post overview)

Thu Apr 18 Sequence to Sequence Models and Machine Translation [slides] [notes (lectures 5 and 6)] Suggested Readings:

1. Statistical Machine Translation slides, CS224N 2015 (lectures 2/3/4)
2. Statistical Machine Translation (book by Philipp Koehn)
3. BLEU (original paper)
4. Sequence to Sequence Learning with Neural Networks (original seq2seq NMT paper)
5. Sequence Transduction with Recurrent Neural Networks (early seq2seq speech recognition paper)
6. Neural Machine Translation by Jointly Learning to Align and Translate (original seq2seq+attention paper)
7. Attention and Augmented Recurrent Neural Networks (blog post overview)
8. Massive Exploration of Neural Machine Translation Architectures (practical advice for hyperparameter choices)
9. Achieving Open Vocabulary Neural Machine Translation with Hybrid Word-Character Models
10. Revisiting Character-Based Neural Machine Translation with Capacity and Compression Assignment 3 out [code] [handout] [latex template] [overleaf link] Assignment 2 due Week 4

Tue Apr 23

Final Projects and LLM intro [slides] Suggested Readings:

1. Practical Methodology (Deep Learning book chapter) Project Proposal out [handout]

Default Final Project out [handout]

Thu Apr 25 Transformers (by Anna Goldie) [slides] [notes] Suggested Readings:

1. Attention Is All You Need
2. The Illustrated Transformer
3. Transformer (Google AI blog post)
4. Layer Normalization
5. Image Transformer
6. Music Transformer: Generating music with long-term structure
7. Jurafsky and Martin Chapter 10 (Transformers and Large Language Models)

Week 5

Tue Apr 30

Pretraining [slides] Suggested Readings:

1. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

2. Contextual Word Representations: A Contextual Introduction

3. The Illustrated BERT, ELMo, and co.

4. Jurafsky and Martin Chapter 11 (Fine-Tuning and Masked Language Models) Assignment 4 out [code] [handout] [overleaf] [colab run script] Assignment 3 due Thu May 2 Post-training (RLHF, SFT, DPO) (by Archit Sharma) [slides] Suggested Readings:

5. Aligning language models to follow instructions

6. Scaling Instruction-Finetuned Language Models

7. AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback

8. How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources

9. Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Fri May 3 Hugging Face Transformers Tutorial Session [colab] * * 3:30pm - 4:20pm Gates B03 Project Proposal due

Week 6

Tue May 7

Benchmarking and Evaluation (by Yann Dubois) [slides] Suggested Readings:

1. Challenges and Opportunities in NLP Benchmarking
2. Measuring Massive Multitask Language Understanding
3. Holistic Evaluation of Language Models
4. AlpacaEval

Thu May 9 Efficient Neural Network Training (by Shikhar Murty) [slides] Suggested readings:

1. Mixed Precision Training
2. ZeRO: Memory Optimizations Toward Training Trillion Parameter Models
3. PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel
4. LoRA: Low-Rank Adaptation of Large Language Models Final Project Proposals Returned

Project Milestone out [handout]

Assignment 4 due Week 7

Tue May 14

Speech Brain-Computer Interface (by Chaofei Fan) [slides] Suggested readings:

1. A high-performance speech neuroprosthesis
2. An accurate and rapidly calibrating speech neuroprosthesis
3. A high-performance neuroprosthesis for speech decoding and avatar control
4. Brain-Machine Interfaces (Principles of Neural Science chapter)

Thu May 16 Reasoning and Agents (by Shikhar Murty) [slides] Suggested readings:

1. Orca: Progressive Learning from Complex Explanation Traces of GPT-4

2. Least-to-Most Prompting Enables Complex Reasoning in Large Language Models

3. ReAct: Synergizing Reasoning and Acting in Language Models

4. BAGEL: Bootstrapping Agents by Guiding Exploration with Language

5. WebArena: A Realistic Web Environment for Building Autonomous Agents Additional Readings:

6. Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks

7. Response: Emergent analogical reasoning in large language models

8. WebLINX: Real-World Website Navigation with Multi-Turn Dialogue

Week 8

Tue May 21

Life after DPO (by Nathan Lambert) [slides] Suggested readings:

1. RewardBench: Evaluating Reward Models for Language Modeling
2. D2PO: Discriminator-Guided DPO with Response Evaluation Models
3. Social Choice for AI Alignment: Dealing with Diverse Human Feedback

Wed May 22 Final Project Milestone due Thu May 23 ConvNets, Tree Recursive Neural Networks and Constituency Parsing [slides] Suggested readings (tentative):

1. Convolutional Neural Networks for Sentence Classification
2. Improving neural networks by preventing co-adaptation of feature detectors
3. A Convolutional Neural Network for Modelling Sentences
4. Parsing with Compositional Vector Grammars.
5. Constituency Parsing with a Self-Attentive Encoder Final Project Report Instructions out [Instructions] Fri May 24 Course Withdrawal Deadline Week 9

Tue May 28

An Introduction to Responsible NLP (by Adina Williams) Suggested readings:

1. Preface + Introduction chapter of the FairML book by Solon Barocas, Moritz Hardt, Arvind Narayanan
2. Introducing v0.5 of the AI Safety Benchmark from MLCommons Final Project Milestones Returned Thu May 30 NLP, linguistics, and philosophy [slides] Suggested readings: Week 10

Tue June 4

Final Project Emergency Assistance (no lecture) Extra project office hours available during usual lecture time, see Ed. Thu June 6 No class Final project due Mon June 10 Final Project Poster Session ** 11 am - 3 pm [More details] Location: McCaw Hall and Ford Gardens On-campus students must attend in person! [Printing guide]