PCA 2025 Overview

Course overview for the Project Conversational Agents

This page contains all pertinent project information. Go through it section by section to find out how to succeed in this course and find any relevant details you need to successfully complete this project.

Project Introduction

This project focuses on building a task-based conversational agent capable of recommending recipes from a database of nearly 1,000 options. The agent will use speech as its primary mode of interaction while also incorporating a visual interface to display relevant information, ensuring alignment between these two modalities. Users will interact with the agent by specifying preferences and constraints, such as ingredients, cooking time, or type of dish, and the agent must understand and respond effectively to their inputs. A key challenge is designing an agent that can handle the variability in how users express their needs and conduct conversations, while also reasoning over the broad knowledge space of recipes to provide accurate recommendations. Starting with a Prolog database and a basic agent template, the project will involve developing essential conversational capabilities, systematically testing the agent, and refining its performance. Teams are encouraged to add creative features to enhance the agent’s functionality, culminating in a fully operational system that can assist users in finding recipes they would love to cook.

How is this Project Course Organized?

Course Schedule

The project course Conversational Agents (code XB_0101) runs in period 3 (Jan to Feb 2025). Lectures each week are scheduled on Tuesdays from 13:30 to 15:15 in the Theater 1 NU building and Thursdays from 13:30 to 15:15 in MF-FG2.

Practical sessions are scheduled each week on Tuesdays from 15:30 to 19:15 and Fridays from 13:30 to 17:15.

Attendance at all practical sessions is mandatory. Missing sessions without prior approval will result in failure of the course.

Rules:

  1. Be On Time: Arrive within the first 30 minutes. Late arrivals beyond this will be marked absent.

  2. Stay at least 2 Hours: Leaving early without approval is considered non-attendance.

  3. Active Participation: Simply being present without contributing is not acceptable.

If You Cannot Attend:

  • Email [Instructor’s Email] before the session, explaining your absence, this will then be discussed with the teaching staff to see if an exception can be made.

Consequences:

Failure to comply with these rules will result in course failure, regardless of performance in other areas.

Take this seriously, no exceptions will be made.

Go here for the detailed Course Schedule.

Getting Started!

Form a group of 6

Section Goal: Form a group of 6 members (including yourself) to complete the project.

Steps to Join or Form a Group:

  1. Find a Group on Your Own:

    • If you have a group of 6, ensure all members are officially joined under the same group on Canvas.

  2. Need Help Finding a Group?

    • Use Canvas to join an available group under one of the sections (Group Set: B, E, EE, I, J, L, M, MR) then choose a group like B1, M3, etc.

    • If you are unable to find a group, assign yourself to a group under the "People" section, or request to be assigned.

  3. Groups Not Yet Full:

    • If your group has fewer than 6 members, join with your group mates on Canvas, and additional members will be assigned to you.

    • By January 7th at 13:30, all incomplete groups will automatically receive additional members to reach the required size of 6.

  4. Deadline for Group Formation:

    • If you are not part of a group by January 7th at 13:30, you must either:

      • Assign yourself to a group.

      • Join an available group under the "Letter Groups" section.

    • Failure to do so will result in the assumption that you are not participating.

Important Times:

  • January 7th, 13:30: Deadline to join or form a group.

  • January 7th, 15:30: Final group assignments will be made for incomplete groups.

Make sure to act promptly to ensure your participation in the project!You will be working on the main project assignment together in a group of 6 students. We will assign a teaching assistant (TA) to each group. Your TA will also monitor whether each of you individually sufficiently contributes to the deliverables. Individual contribution and participation in the course are required to pass the course. Enroll your group members on Canvas in a group.

Preliminaries and Quiz Materials

Section Goal: Individually understand all concepts and tools described on the background knowledge pages. Memorizing every detail is not necessary, but you should have a decent understanding.

Before you begin this project, please make sure that you understand the relevant background knowledge that you will need throughout the project.

Quiz

 

Project Installation

With a basic understanding of the concepts and tools that you will use in this project, you now should proceed with installing all the needed software and tools on your device. Some will be re-used from the MAS course, but others are new. Go to https://socialrobotics.atlassian.net/wiki/spaces/PCA2/pages/2709487855 which has all the details related to installation and computer setup and complete all instructions on this page.

The Project Assignment

You and your team should now be ready to get started on developing your own conversational agent capable of recommending recipes from a given recipe database.

Your Pipeline

Building your Agent

The core of this project surrounds building a recipe recommendation agent as a team. There are different tasks that you will encounter:

We encourage you to work on these assignments as a team as much as possible. Throughout the project go here for instructions on

https://socialrobotics.atlassian.net/wiki/spaces/PCA2/pages/2709487945 .

Testing

Testing your conversational agent continuously is very important during the project. Each week you should collect, analyze, and submit data about how your agent is performing. Your analysis of that data will help to improve your agent. However, testing your own agent yourself is not good enough because developers are not the best testers of their own software.

 

How to pass the course, deliverables & grading

Requirements for successfully completing the project

To complete this course, you must have participated in and completed the following:

Assessment and Grading

Grade Composition

  • Basic Conversational Agent: 30%

  • Extensions to the Agent (quality and originality): 30%

  • Written Report: 30%

  • Individual Quiz: 10%

    • A pass adds 1 full point to the grade.

    • A fail adds no points.

  • Practical Attendance:

    • Pass or Fail

    • Mandatory pass. A failure will lead to failing the entire course.

  • Midway Check-In Presentation:

    • Pass or Fail

    • Mandatory pass. A failure will lead to failing the entire course.

Make sure to also check out the assessment rubrics to get a sense of how various parts will contribute to your grade.

Due Dates

  • Group Formation

    • Due Date: Tuesday, 7 January 2024, by 13:30

    • Task: Form a group of 6 members (including yourself) to complete the project.

  • Project Preliminaries Quiz

    • Due Date: Sunday, 12 January 2025, by 23:59

    • Task: Complete a preliminary quiz to assess foundational understanding. Find project preliminaries here [TBA].

  • Midway Check-In Presentation and Basic Agent - Inclusion

    • Due Date: Friday, 17 January 2025, by 13:00

    • Task: Present progress and receive feedback on your project. Find more information here [TBA].

  • Conversational Agent Code Submission

    • Due Date: Tuesday, 28 January 2025, by 15:00

    • Task: Submit the code for the conversational agent. Find more information here [TBA].

  • Final Submission

    • Due Date: Sunday, 2 February 2025, by 23:59

    • Task: Submit the complete project, including the final report. Find more information here [TBA]

  • The work is graded with a mark from 0-100. There must be a minimum of 55 to pass the course.

  • Individuals may be rewarded a higher or lower grade than the group based on their effort and their contribution to the teamwork.

Communication & Contact policy

For communication throughout this project course, we will use Canvas Discussion Boards between practical sessions. These will be answered on Mondays, Wednesdays, and Thursdays.

Your main point of contact and question-answering will be during the 4 hour-long practical sessions on Tuesdays and Fridays. This is where most concerns about project content will be handled.

For group, organizational, or absence-related issues please contact [Instructor’s Email].

If the question or issue cannot be resolved with your TA, ask your TA to take this up with us. Only if after that you still have not received any response within a reasonable time (within a week that means), send the teachers a mail.

Inclusivity Statement

We strive to offer students a safe and inclusive classroom environment. We welcome the perspective of students of all ethnicities, genders, spiritual beliefs, and sexual orientations, among others. If you feel discriminated based on your identity, please report it to the course staff.

If you have a disability and require accommodations, please let us know before the beginning of the course so that we can discuss your accommodations and needs to make the course as accessible to you as possible.

Academic integrity and code of conduct

Plagiarism is not tolerated in both reports and codes. You are welcome to use any code you see fit for your project, as long as you appropriately cite your sources both in the report and in the code itself (as comments). Behavior violating the VU rules for academic integrity will not be tolerated.