Assessing an Email-Filtering Feature Proposal
Case context: A mail-security team is considering several design options. One proposal is to create features whose role is to capture meaning from the words and phrases in incoming messages.
Question: Does this proposal follow the stated direction? Explain why or why not.
Sample answer: Yes. The proposal matches the direction because it calls for feature creation, and those features are intended to interpret the message text itself.
Key points:
- The correct decision is yes.
- The proposal is about building features.
- Those features are meant to capture meaning from email text.
- The proposal fits the email-filtering setting.
Rubric: The response should give the correct decision and support it with both required ideas: feature construction and using those features to interpret the message text.
0
1
Tags
Machine Learning
Deep Learning
Machine Learning Strategy
Supervised Learning
Dive into Deep Learning @ D2L
Data Science
Machine Learning Yearning @ DeepLearning.AI
Related
Which proposed anti-spam direction is centered on the email's meaning?
Text-based feature ideas for email filtering
Complete the anti-spam direction: Build features that capture the _____ of a message.
Match the elements to their roles in a message-filtering project.
Arrange the steps for choosing the text-based anti-spam approach.
Describe a text-analysis direction for a junk-mail filter.
Assessing an Email-Filtering Feature Proposal
What do the suggested anti-spam features examine?
Which option best separates the modeling task from the information being modeled?
The team treats text analysis as the only possible starting point for an anti-spam system.