Google Professional Machine Learning Engineer Exam - Topic 9 Question 2 Discussion

Actual exam question for Google's Professional Machine Learning Engineer exam

Question #: 2
Topic #: 9

[All Professional Machine Learning Engineer Questions]

You work for a large technology company that wants to modernize their contact center. You have been asked to develop a solution to classify incoming calls by product so that requests can be more quickly routed to the correct support team. You have already transcribed the calls using the Speech-to-Text API. You want to minimize data preprocessing and development time. How should you build the model?

AUse the Al Platform Training built-in algorithms to create a custom model

BUse AutoML Natural Language to extract custom entities for classification

CUse the Cloud Natural Language API to extract custom entities for classification

DBuild a custom model to identify the product keywords from the transcribed calls, and then run the keywords through a classification algorithm

Show Suggested Answer

Suggested Answer: A

by Gail at May 03, 2022, 10:10 PM

Limited Time Offer

25%

Off

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

Contribute your Thoughts:

Submit Cancel

Arlean

5 months ago

Not sure about using built-in algorithms, they might be too generic.

upvoted 0 times

...

Joanne

5 months ago

Wait, can the Cloud Natural Language API really handle this?

upvoted 0 times

...

Gail

5 months ago

Definitely go with option B, it saves time!

upvoted 0 times

...

Hannah

5 months ago

A custom model sounds like too much work for this.

upvoted 0 times

...

Tamar

5 months ago

I think AutoML Natural Language is the way to go!

upvoted 0 times

...

Alesia

5 months ago

Building a custom model sounds like it could give us more control, but it might take longer to develop. I’m leaning towards AutoML, but I’m not completely sure.

upvoted 0 times

...

Pearlene

5 months ago

I practiced a question like this where we had to choose between built-in algorithms and custom models. I feel like going with built-in algorithms might save time, but I'm not confident about the accuracy.

upvoted 0 times

...

Sherrell

5 months ago

I think using the Cloud Natural Language API could be a quick solution since it handles entity extraction well. But I wonder if it can be customized enough for our needs.

upvoted 0 times

...

Mireya

5 months ago

I remember we discussed using AutoML for similar classification tasks in class. It seems like a good fit here, but I'm not entirely sure if it's the best option.

upvoted 0 times

...

Romana

6 months ago

This seems like a straightforward question about HIPAA compliance for a small dental practice. I think the key is to identify the appropriate code set based on the details provided.

upvoted 0 times

...

Agustin

6 months ago

I think I've got it. Implementing the business logic as a custom Spring Bean allows me to reuse it in multiple workflows, and it also lets me autowire dependencies on the Java class implementation. Those seem like the two best options here.

upvoted 0 times

...

Amie

6 months ago

Okay, let me think this through. Relational databases are a core part of many enterprise applications, so the answer is likely to be a well-known Microsoft server technology. I'm going to go with option D, Microsoft SQL Server.

upvoted 0 times

...

Minna

6 months ago

Hmm, I'm not sure about this one. I was thinking the question about data partitioning might be more relevant, but I'm a bit confused on the best approach here. I'll have to think it through a bit more.

upvoted 0 times

...