Which of the following statements are true about the differences between using convolutional neural networks (CNNs) in text tasks and image tasks?
A.
Color image input is multi-channel, whereas text input is single-channel.
B.
When the CNN is used for text tasks, the kernel size must be the same as the number of word vector dimensions. This constraint, however, does not apply to image tasks.
C.
For CNN, there is no difference in handling text or image tasks.
D.
CNNs are suitable for image tasks, but they perform poorly in text tasks.
A:True — color images have multiple channels (e.g., RGB = 3), while text inputs are represented as sequences of word embeddings, typically single-channel in structure.
B:True — in text tasks, the convolution kernel height must match the embedding dimension to capture complete token information, which is not a constraint in images.
C:False — there are clear differences in handling between text and image data.
D:False — CNNs can perform very well in text classification when used appropriately.
Exact Extract from HCIP-AI EI Developer V2.5:
"In text CNNs, convolution kernels span the entire embedding dimension, whereas in image CNNs, kernel size is independent of channel count."
[Reference:HCIP-AI EI Developer V2.5 Official Study Guide – Chapter: CNN in NLP, ]
Contribute your Thoughts:
Chosen Answer:
This is a voting comment (?). You can switch to a simple comment. It is better to Upvote an existing comment if you don't have anything to add.
Submit