Deal of The Day! Hurry Up, Grab the Special Discount - Save 25% - Ends In 00:00:00 Coupon code: SAVE25
Welcome to Pass4Success

- Free Preparation Discussions
Mail Us support@pass4success.com
Location US
Mob_nav_barsMENU

Google Professional Machine Learning Engineer Exam - Topic 6 Question 64 Discussion

Actual exam question for Google's Professional Machine Learning Engineer exam
Question #: 64
Topic #: 6
[All Professional Machine Learning Engineer Questions]

You work for a hotel and have a dataset that contains customers' written comments scanned from paper-based customer feedback forms which are stored as PDF files Every form has the same layout. You need to quickly predict an overall satisfaction score from the customer comments on each form. How should you accomplish this task'?

Show Suggested Answer Hide Answer
Suggested Answer: D

Applying quantization to your SavedModel by reducing the floating point precision can help reduce the serving latency by decreasing the amount of memory and computation required to make a prediction. TensorFlow provides tools such as the tf.quantization module that can be used to quantize models and reduce their precision, which can significantly reduce serving latency without a significant decrease in model performance.


by Stevie at Sep 02, 2023, 02:39 AM

Limited Time Offer

25%

Off

Get Premium Professional Machine Learning Engineer Questions as Interactive Web-Based Practice Test or PDF

Contribute your Thoughts:

0/2000 characters
Submit Cancel
Bev
6 months ago
Totally agree with A, it's straightforward!
upvoted 0 times
...
Margart
6 months ago
Wait, can the Vision API really handle all that?
upvoted 0 times
...
Ellen
6 months ago
D seems a bit overkill for just sentiment analysis.
upvoted 0 times
...
Eleni
6 months ago
I think C could work too, but not sure.
upvoted 0 times
...
Margurite
7 months ago
Sounds like A is the best option!
upvoted 0 times
...
Peter
7 months ago
I recall a similar question where we had to choose between custom extractors and standard APIs. I wonder if the Document AI custom extractor is necessary for this task.
upvoted 0 times
...
Paris
7 months ago
I’m a bit confused about whether to use analyzeEntitySentiment or just analyzeSentiment. I think they serve different purposes, right?
upvoted 0 times
...
Denny
7 months ago
I remember practicing with sentiment analysis, and I feel like the analyze sentiment feature is what we need for overall satisfaction scores.
upvoted 0 times
...
Jin
7 months ago
I think we talked about using the Vision API for text extraction, but I'm not sure if it's the best option here.
upvoted 0 times
...
Jannette
7 months ago
I'm a bit confused by all the different API options. I'm leaning towards option C since it sounds like it might be the most robust approach, but I'll need to do some more research on how to set up a custom Document AI extractor.
upvoted 0 times
...
Huey
7 months ago
I think option B with the analyzeEntitySentiment feature could be interesting. That might give me more nuanced insights into the customer feedback beyond just the overall sentiment.
upvoted 0 times
...
Emogene
7 months ago
Hmm, I'm not sure if that's the best approach. The question mentions the comments are stored in PDF files, so I might try option C and use a Document AI custom extractor to parse the text first before feeding it to the Natural Language API.
upvoted 0 times
...
Leah
7 months ago
This seems like a straightforward task - I'd go with option A. Using the Vision API to extract the text and then the Natural Language API's analyzeSentiment feature should give me the overall satisfaction scores pretty quickly.
upvoted 0 times
...
Joesph
7 months ago
Option A seems like the quickest and most straightforward way to get the job done. As long as the PDF formatting is consistent, I think that'll be the best approach to tackle this exam question efficiently.
upvoted 0 times
...
Shannan
7 months ago
Integrating the community is a smart move in my opinion. They can provide a fresh perspective and catch things the internal team might overlook. As long as you're careful about what you share, it's worth the effort.
upvoted 0 times
...
Gearldine
7 months ago
I've got a good feeling about this one. Based on my understanding of backup solutions, SnapCenter is likely designed to keep the transaction logs intact rather than deleting or truncating them. I'll go with that as my initial answer.
upvoted 0 times
...
William
7 months ago
A functional global variable might be an interesting way to go, but I'm not sure if that's the most efficient or recommended solution. I'll have to weigh the different options and decide which one seems like the best fit for this scenario.
upvoted 0 times
...
Dorinda
1 year ago
Hmm, I don't know. Option A seems like the simplest approach, and sometimes simple is best, you know? Plus, I heard the Vision API is getting pretty good at handling scanned PDFs these days.
upvoted 0 times
Colby
11 months ago
I see your point, but I think sticking with Option A might be more efficient.
upvoted 0 times
...
Margo
11 months ago
C) Uptrain a Document AI custom extractor to parse the text in the comments section of each PDF file. Use the Natural Language API analyze sentiment feature to infer overall satisfaction scores.
upvoted 0 times
...
Willetta
12 months ago
Yeah, I agree. Option A does seem like the most straightforward choice.
upvoted 0 times
...
Santos
1 year ago
A) Use the Vision API to parse the text from each PDF file Use the Natural Language API analyzesentiment feature to infer overall satisfaction scores.
upvoted 0 times
...
Tresa
1 year ago
Let's go with Option A then. It seems like the most efficient choice.
upvoted 0 times
...
Peggie
1 year ago
I agree, simplicity is key. The Vision API has been improving a lot lately.
upvoted 0 times
...
Janessa
1 year ago
Option A) Use the Vision API to parse the text from each PDF file Use the Natural Language API analyzesentiment feature to infer overall satisfaction scores.
upvoted 0 times
...
...
Rolande
1 year ago
Haha, I'm feeling a bit sentimental about this question. Option D all the way, baby! Gotta get that entity-level sentiment analysis going on. It's like a fine-tuned sentiment smoothie for my hotel's feedback data.
upvoted 0 times
...
Brandee
1 year ago
I'm gonna go with option B. The analyzeEntitySentiment feature could give us some more granular insights into the customer's sentiments, right? That could be really useful for this kind of task.
upvoted 0 times
...
Rodney
1 year ago
The correct answer is C. Using the Vision API to extract the text from the PDF files and then leveraging the Natural Language API's analyzeSentiment feature is the way to go. Seems straightforward and efficient.
upvoted 0 times
...
King
1 year ago
I see both points, but I think option D might be the most comprehensive approach. By uptraining a custom extractor and using analyzeEntitySentiment, we can capture both sentiment and entities for a more detailed analysis.
upvoted 0 times
...
Susana
1 year ago
I disagree, I believe option C is more suitable. By uptraining a custom extractor, we can focus on the comments section for better accuracy in predicting satisfaction scores.
upvoted 0 times
...
Hayley
1 year ago
I think option A is the best choice because we can use the Vision API to extract text and then analyze sentiment to predict satisfaction scores.
upvoted 0 times
...

Save Cancel