General Information
| Course Code | XB_0182 |
|---|---|
| Credits | 6 EC |
| Period | P4 |
| Course Level | 300 |
| Language of Tuition | English |
| Faculty | Faculty of Science |
| Course Coordinator | dr. J. Pei |
| Examiner | dr. J. Pei |
| Teaching Staff |
dr. J. Pei prof. dr. K.V. Hindriks |
|
Part of programme(s)
Bachelor
Use the arrow keys to navigate the list, Enter to select, and Escape to close.
|
|
Practical Information
You need to register for this course yourself. The (de)registration deadlines can be found on VU.nl
| Teaching Methods | Seminar, Written partial exam, Lecture |
|---|
Course Objective
- Develop a conversational agent by developing a simple ontology for a knowledge base for the cooking domain which enables the agent to reason about recipes (Applying knowledge and understanding)
- Apply and understand conversation design patterns (Applying knowledge and understanding)
- Design and implement visual support for different stages in the conversation (Applying knowledge and understanding)
- Evaluate a prototype conversational agent for the cooking domain (Making judgments)
- Plan and organize work together in a project group using appropriate tools (Applying knowledge and understanding)
Course Content
Students learn how to develop a cognitive dialogue agent that uses Google's DialogFlow and builds on the natural conversation framework of Robert Moore. Groups will collaborate todevelop a conversational agent for the cooking domain, with a focus on the recipe selection task in this domain. They will design and implement domain knowledge, conversational patterns, natural language understanding and visuals. The agent will be a recipe recommendation assistant with visual support that supports the user to find a suitable cooking recipe.
Additional Information Teaching Methods
Lectures, lab sessions (with computer/ laptops). Attendance at labs is obligatory. Students will work in groups of 6.
Method of Assessment
The grade is based on the quality of the basic conversational agent (30%), the quality and originality of extensions to the basic agent (30%), and the written report (30%).
In addition, students are required to complete an exam that assesses their understanding of course content and their ability to evaluate conversational agents (10%). The exam will be one hour long and proctored by TAs.
Each component needs to be at least graded with a 5.5 or higher to pass this course.
There will be resit options, and the maximum grade will be capped at 5.5 if the student passes.
Literature
Conversational UX Design: A Practitioner's Guide to the Natural Conversation Framework
Robert J Moore en Raphael Arar | 29 mei 2019
ISBN-10: 1450363024
ISBN-13: 978-1450363020
A cognitive agent programming guide (online)
- Learn Prolog Now! (online)
- Github tutorial (online)
- Bootstrap tutorial (online)
- Dialogflow tutorial (online)
- Natural language understanding models (online)
Additional Information Target Audience
Bachelor Artificial Intelligence
Additional Information
Level 3 Use of generative AI is permitted, with explanation and reflection
In this course, generative AI (GenAI), such as ChatGPT or similar tools, may be used as part of the working process. The student must explicitly explain how GenAI was used and critically reflect on the quality, usefulness, and limitations of the output. Assessment also focuses on how GenAI has been used consciously, critically, and responsibly. Incorrect use of GenAI, including failure to comply with the requirements for explanation and reflection, is considered fraud. If established, the submitted work or assessment result will be declared invalid, and the Examination Board may impose further measures.
Recommended background knowledge
You should have completed Multi-Agent Systems (XB_0024)