Your report should briefly 1. explain your agent’s conversational competence (how can a user interact with it), 2. motivate your design choices, 3. present the testing data you collected, 4. interpret the results from testing your agent, and 5. present the overall findings and lessons learned of your project.

Your report needs to have the following structure, and should comply with the maximum page limit indications for each section:

...

Extensions to bot (not including hpo and model updates)

Pilot User Study

Conclusion

1. Title (0.5 page)

Content:

• Add the report title.

• Include group number, student names, emails, and student numbers right below title.

...

2. Introduction (1 page)

Content:

• Briefly introduce the project: What is a conversational recipe recommendation agent?

• State the goals your team aimed to achieve.

• Mention the report structure and highlight key components (e.g., how exclusion and user study are critical).

Tips:

• Ensure clarity and conciseness. This section sets the stage for the reader.

• Provide some background on the significance of conversational agents in recipe recommendation.

...

3. How Does Your Conversational Agent Work? (2 pages)

Content:

• Explain the overall functionality of your agent.

  • What problems does it solve?

  • What can users achieve by interacting with the agent?

• Describe the conversational flow:

  • Main features (e.g., recipe suggestions, ingredient substitutions).

  • Supported interactions (e.g., asking for specific cuisines, excluding allergens).

• Functional specification:

  • Technical summary of how the agent is designed (without getting overly detailed yet).

Tips:

• Include examples of interactions (e.g., “User: Show me vegan recipes. Agent: Here are some vegan options”).

• Keep it simple and user-focused.

...

4. Intent and Slot Classifier (2 pages)

Content:

• Explain the role of the intent and slot classifier in the agent.

• Performance analysis:

  • Metrics: Accuracy, precision, recall, F1 score, confusion matrix.

  • Any improvements made, such as additional training data or custom models.

• Discuss challenges:

  • Ambiguous intents or overlapping slots and how these were addressed.

• Extensions to the model:

  • Example: Use of pre-trained embeddings, custom layers, or domain-specific tuning.

Tips:

• Include visual aids such as tables or charts to present performance data effectively.

• Highlight innovative solutions your team implemented.

...

5. Exclusion (2 pages)

Content:

• Implementation:

  • How exclusion works (e.g., filtering ingredients, cuisines, and tags).

  • Approaches used: intent-based, slot-based, rule-based, classifier-based.

  • Tools/technologies: Integration of MARBEL, Prolog, Python, and ontology updates.

• Testing:

  • Comparison of inclusion-only vs. exclusion models.

  • Examples of exclusion in action (e.g., excluding dairy, gluten, or specific cuisines).

• Performance Analysis:

  • Accuracy with and without exclusion.

  • Trade-offs and impact on user satisfaction.

• Pros and Cons:

  • Discuss strengths and limitations of the exclusion mechanism.

Tips:

• Use examples and data to illustrate the effectiveness of the exclusion approach.

• Be critical and discuss what could be improved.

...

6. Extensions to the Bot (1 page)

Content:

• Describe additional enhancements:

  • New functionalities added.

  • Improvements in user interaction and experience (e.g., better response generation, conversational adaptability).

• Explain the motivation and impact of these extensions.

Tips:

• Highlight how these extensions make the bot stand out beyond baseline requirements.

...

7. Pilot User Study (1.5 pages)

Content:

• Setup:

  • Who were the users?

  • What tasks were they asked to perform?

  • Methodology for data collection (e.g., surveys, observation, interaction logs).

• Results:

  • Quantitative data: Success rates, error rates, average response time, etc.

  • Qualitative data: User feedback, observations of user behavior.

• Analysis:

  • Key findings: What worked well? What needs improvement?

  • Lessons learned and implications for future work.

Tips:

• Use charts or graphs to present quantitative findings.

• Include excerpts from user feedback to illustrate qualitative insights.

...

8. Conclusion (1 page)

Content:

• Summarize the main outcomes of the project.

• Reflect on the process:

  • What went well (e.g., teamwork, innovative solutions)?

  • What could be improved (e.g., time management, data quality)?

• Suggest future improvements or extensions.

Tips:

• Keep it concise but reflective.

• Focus on high-level takeaways and actionable insights for future work.

Title

Add a title. Add your group number, student names, emails, and student numbers right below the title.

...