New Year Sale 2026! Hurry Up, Grab the Special Discount - Save 25% - Ends In 00:00:00 Coupon code: SAVE25
Welcome to Pass4Success

- Free Preparation Discussions

Microsoft DP-100 Exam - Topic 6 Question 77 Discussion

Actual exam question for Microsoft's DP-100 exam
Question #: 77
Topic #: 6
[All DP-100 Questions]

You are building a machine learning model for translating English language textual content into French

language textual content.

You need to build and train the machine learning model to learn the sequence of the textual content.

Which type of neural network should you use?

Show Suggested Answer Hide Answer
Suggested Answer: C

To translate a corpus of English text to French, we need to build a recurrent neural network (RNN).

Note: RNNs are designed to take sequences of text as inputs or return sequences of text as outputs, or both.

They're called recurrent because the network's hidden layers have a loop in which the output and cell state from each time step become inputs at the next time step. This recurrence serves as a form of memory. It allows contextual information to flow through the network so that relevant outputs from previous time steps can be applied to network operations at the current time step.


https://towardsdatascience.com/language-translation-with-rnns-d84d43b40571

Contribute your Thoughts:

0/2000 characters
Linwood
4 months ago
MLPs won't cut it for this task, no way!
upvoted 0 times
...
Simona
4 months ago
Surprised RNNs are still the go-to choice!
upvoted 0 times
...
Lashon
4 months ago
Wait, aren't CNNs also used for text?
upvoted 0 times
...
Rossana
4 months ago
Totally agree, RNNs handle text well.
upvoted 0 times
...
Micaela
5 months ago
RNNs are the best for sequence data!
upvoted 0 times
...
Golda
5 months ago
GANs are cool for generating data, but I don't think they would work for translation tasks. RNNs sound like the right choice here.
upvoted 0 times
...
Larue
5 months ago
I feel like MLPs might not capture the sequential nature of language well enough. RNNs seem like the best fit.
upvoted 0 times
...
Percy
5 months ago
I remember practicing with a similar question, and I think CNNs are more for image data, not text.
upvoted 0 times
...
Kanisha
5 months ago
I think we should use RNNs because they are designed for sequence data, right? But I'm not completely sure.
upvoted 0 times
...
Rodrigo
5 months ago
I feel pretty good about this one. Net income is the bottom line figure that represents the company's earnings available to shareholders after all expenses, including debt and taxes, have been accounted for. I'm going to go with C.
upvoted 0 times
...
Valentin
5 months ago
I'm not sure about this one. The management interface seems like the most logical choice, but I'm not 100% confident.
upvoted 0 times
...
Rodrigo
5 months ago
I practiced a similar question about navigation tools last week. I feel like descriptive page headings might work well, but I'm not 100% sure if they're enough on their own.
upvoted 0 times
...

Save Cancel