AI-403-paul.wilmoth-2026-08-20-01-14-13
Below is a syllabus template that includes WSU's required syllabus elements. Please complete all items highlighted in yellow.
Title of Course [Natural Language Processing and Conversational AI]
Prefix and Number [AI 403]
Semester and Year [tbd]
Number of Credit Hours [3]
Prerequisites [AI 240 Foundations of Artificial Intelligence]
Course Details
Day and Time: [tbd]
Meeting Location: [tbd]
Instructor Contact Information
Instructor Name: [tbd]
Instructor Contact Information: [office location, phone, email] [tbd]
Instructor Office Hours: [click here for best practices] [tbd]
TA Name: [tbd]
TA Contact Information: [office location, phone, email]: [tbd]
TA Office Hours: [click here for best practices] [tbd]
Course Description
[AI 403, Natural Language Processing and Conversational AI, examines how computational systems represent, understand, generate, and interact through human language. Students study text processing and corpora, sparse and dense representations, language modeling, sequence modeling, recurrent models, attention, transformer architectures, and recent advances in discrete diffusion models and flow-based language models. They implement and compare methods for text classification, information extraction, question answering, summarization, and text generation. Building on pretrained language models, students apply fine-tuning, parameter-efficient adaptation, prompting, and retrieval-augmented generation to design conversational systems with grounding, dialogue state, multi-turn context, and tool use. Students evaluate systems using task-based efficiency, robustness, and human-centered measures and conduct systematic error and failure analysis. The course addresses hallucination, bias, toxicity, privacy, safety, multilingual aspects, accessibility, and societal impacts. A culminating project requires students to design, implement, evaluate, and communicate a natural-language or conversational AI application.]
Course Materials
Books: [No textbook is required. Instructor-selected readings, research papers, tutorials, and software documentation will be provided or linked through Canvas at no cost to students.]
Other Materials: [Students will use Python, Jupyter notebooks, PyTorch, and selected NLP libraries. Instructor-provided notebooks, datasets, and model checkpoints will support programming activities. Required exercises will be designed for local or no-cost computing environments using small models and limited datasets. No paid API subscription, cloud-computing subscription, or dedicated GPU purchase is required. Additional required software and materials cost: $0.]
Fees: [No additional course-specific fees are proposed.]
|
Course Learning Outcomes (students will be able to:) |
Activities Supporting the Learning Outcomes | Assessment of the Learning Outcomes |
|---|---|---|
|
1. Explain and compare how natural language processing systems represent, model, and generate language using sparse, neural, and pretrained approaches (6a, 7g). |
Lectures, guided readings, architecture discussions, and model demonstrations |
Quizzes and architecture-analysis assignment |
|
2. Prepare and represent text data, including tokenization, normalization, corpus construction, and static and contextual embeddings (1c, 1e, 6a). |
Data-preparation exercises and programming laboratories |
Text-processing and representation laboratory |
|
3. Implement and compare sequence, attention, and transformer-based methods for core NLP tasks such as classification, sequence labeling, information extraction, and text generation (2e, 2g, 6a, 6b, 6c). |
Guided experiments, model-comparison activities, and programming laboratories |
Neural NLP modeling assignment |
|
4. Adapt pretrained language models using fine-tuning, parameter-efficient methods, prompting, and retrieval-augmented generation (1d, 2a, 2c, 2g, 6a, 6f). |
Adaptation laboratories, prompting exercises, retrieval experiments, and project checkpoints |
Language-model adaptation and RAG assignment |
|
5. Design and implement conversational AI systems with grounding, dialogue state, multi-turn context, and tool use (2a, 2c, 2g, 6a, 6f). |
Design workshops, dialogue-system laboratories, and project checkpoints |
Conversational system implementation and project milestone |
|
6. Evaluate natural language and conversational systems using appropriate task-based, efficiency, robustness, and human-centered measures, including systematic error and failure analysis (2e, 6b, 6c, 6d, 6e). |
Benchmark design, evaluation laboratories, error analysis, and case studies |
System evaluation assignment and final project evaluation report |
|
7. Analyze the reliability, risks, and responsible deployment implications of language technologies, including hallucination, bias, toxicity, privacy, safety, multilinguality, accessibility, and societal impact (4a, 4f, 6e, 6f). |
Failure analysis, responsible-AI case studies, risk analysis, red-team exercises, and model-card development |
Reliability and responsible deployment analysis |
|
8. Communicate clearly the design, results, limitations, risks, and implications of a natural language or conversational AI system through technical documentation and presentation (3a, 3b, 3c, 3d, 3e, 6c, 6e). |
Technical writing, design reviews, peer feedback, and presentations |
Final technical report and project presentation |
| Dates | Lesson Topic | Assignment | Assessment |
|---|---|---|---|
|
Week 1 |
Introduction to NLP and conversational AI; core tasks, corpora, and data provenance. | Environment setup; task and dataset exploration. | Ungraded diagnostic and setup check. |
| Week 2 [dates] |
Text preprocessing, normalization, tokenization, and sparse representations. | Begin text-processing and representation laboratory. | Formative feedback on preprocessing and data preparation. |
| Week 3 [dates] |
Static embeddings, similarity, and text-classification baselines. | Compare sparse and dense representations; continue representation laboratory. | Quiz 1. |
| Week 4 [dates] |
Language modeling and recurrent sequence models; neural-modeling fundamentals. | Complete representation laboratory; begin neural NLP modeling assignment. | Text-processing and representation laboratory due. |
| Week 5 [dates] |
Sequence labeling, information extraction, encoder-decoder models, and attention. | Guided implementation and model-comparison experiments. | Formative feedback on neural NLP experiments. |
| Week 6 [dates] |
Transformer architectures, contextual embeddings, and language-model pretraining. | Compare recurrent and transformer-based methods. | Quiz 2. |
| Week 7 [dates] |
Autoregressive generation, decoding, question answering, and summarization. | Complete neural NLP modeling assignment; analyze generated outputs. | Neural NLP modeling assignment due. |
| Week 8 [dates] |
Discrete diffusion models and flow-based language models. | Guided model demonstrations; architecture comparison; project planning. | Architecture-analysis assignment due. |
| Week 9 [dates] |
Fine-tuning and parameter-efficient adaptation of pretrained language models. | Begin language-model adaptation and RAG assignment; develop project proposal. | Final project proposal due. |
| Week 10 [dates] |
Prompting, in-context learning, and sensitivity to prompt design. | Compare prompting and adaptation strategies on a common task. | Quiz 3. |
| Week 11 [dates] |
Retrieval-augmented generation, grounding, and retrieval-based question answering. | Build and test a retrieval-grounded generation pipeline. | Language-model adaptation and RAG assignment due. |
| Week 12 [dates] |
Dialogue management, dialogue state, multi-turn context, and tool use. | Implement and demonstrate a conversational-system prototype. | Final project prototype milestone due. |
| Week 13 [dates] |
Task-based, efficiency, robustness, and human-centered evaluation; error and failure analysis. | Benchmark systems and analyze failures using a documented evaluation protocol. | System evaluation assignment due; Quiz 4. |
| Week 14 [dates] |
Responsible deployment: hallucination, bias, toxicity, privacy, safety, multilinguality, accessibility, and societal impact. | Responsible-AI case study, red-team exercise, and model-card development. | Reliability and responsible deployment analysis due. |
| Week 15 [dates] |
System integration, technical communication, and project presentations. | Present project results; finalize technical report and reproducible repository. | Project presentation. Final report and repository due during finals week; date to be announced. |
Expectations for Student Effort
[Describe how much time students should expect to invest in the course each week. Graduate courses should state: "For each hour of lecture equivalent, students should expect to have a minimum of two hours of work outside of class." Note that Global campus courses will automatically include credit hour equivalents in the syllabus.]
For each hour of lecture equivalent, students should expect to have a minimum of two hours of work outside of class. For this 3-credit course, students should plan for approximately three lecture-equivalent hours and at least six hours of outside work each week, including reading, programming, analysis, quiz preparation, and project work.
Grading [add more lines if necessary]
| Type of Assignment (tests, papers, etc) | Points | Percent of Overall Grade |
|---|---|---|
| Assignments and laboratories (text-processing and representation laboratory: 100pts; neural NLP modeling assignment: 100pts; language-model adaptation and RAG assignment: 100pts; architecture-analysis assignment: 50pts; system evaluation assignment: 50pts; reliability and responsible deployment analysis: 50pts) | 450 | 45% |
| Four quizzes, 50 points each | 200 | 20% |
| Final project, including milestones, technical report, repository, and presentation (proposal 30pts; prototype milestone 60pts; final technical report and repository 150pts; presentation 60pts) | 300 | 30% |
| Attendance | 50 | 5% |
| Total | 1000 | 100% |
| Grade | Percent | Grade | Percent |
|---|---|---|---|
| A |
93% to 100% |
C | 70% to <74% |
| A- | 90% to <93% | C- | 66% to <70% |
| B+ | 86% to <90% | D+ | 62% to <66% |
| B | 82% to <86% | D | 58% to <62% |
| B- | 78% to <82% | F | Below 58% |
| C+ | 74% to <78% |
[Provide information about how grades will be rounded (eg, if 89% earns a B+ and 90% earns an A-, what grade is given to a student with an 89.5?]
The final course percentage is calculated as the total points earned, including attendance, divided by 1,000 and multiplied by 100. Letter grades are assigned using the unrounded percentage and the ranges above. Percentages are not rounded up to the next grade boundary. For example, 89.5% earns a B+, while 90.0% earns an A-.
Attendance and Make-Up Policy
[Provide details on how attendance affects final course grades. Indicate whether and how missed exams, laboratory sessions, etc. can be made up. Sample attendance statement: “Students should make all reasonable efforts to attend all class meetings. However, in the event a student is unable to attend a class, it is the responsibility of the student to inform the instructor as soon as possible, explain the reason for the absence (and provide documentation, if appropriate), and make up class work missed within a reasonable amount of time, if allowed. Missing class meetings may result in reducing the overall grade in the class.” ]
Attendance accounts for 5% of the final course grade (50 points). Attendance will be recorded at each scheduled class meeting that is held. All counted meetings have equal weight. Attendance points = 50 × (number of counted meetings attended / number of counted meetings held). Approved excused absences are removed from the calculation and do not reduce the attendance score. Unexcused absences receive no attendance credit.
Students who cannot attend a class or scheduled assessment should notify the instructor as soon as possible and arrange to review missed material. Requests for excused absences, make-up quizzes, alternative laboratory activities, or deadline extensions due to illness, emergencies, university-recognized absences, or approved accommodations will be handled in accordance with applicable university policies. Whenever feasible, arrangements should be made before the missed activity. Missed graded work receives zero unless a make-up, extension, or other accommodation has been approved.
Academic Integrity Statement
You are responsible for reading WSU's Academic Integrity Policy, which is based on Washington State law. If you cheat in your work in this class you will:
-[Receive a zero on the assignment, quiz, or project component in which the academic-integrity violation occurred.]
-Be reported to the Center for Community Standards
-Have the right to appeal my decision
-Not be able to drop the course of withdraw from the course until the appeals process is finished
If you have any questions about what you can and cannot do in this course, ask me.
If you want to ask for a change in my decision about academic integrity, use the form at the Center for Community Standards website. You must submit this request within 21 calendar days of the decision.