Discuss Google Professional Machine Learning Engineer Exam Topic 4 Question 112

You have a large corpus of written support cases that can be classified into 3 separate categories: Technical Support, Billing Support, or Other Issues. You need to quickly build, test, and deploy a service that will automatically classify future written requests into one of the categories. How should you configure the pipeline?

AUse the Cloud Natural Language API to obtain metadata to classify the incoming cases.

BUse AutoML Natural Language to build and test a classifier. Deploy the model as a REST API.

CUse BigQuery ML to build and test a logistic regression model to classify incoming requests. Use BigQuery ML to perform inference.

DCreate a TensorFlow model using Google's BERT pre-trained model. Build and test a classifier, and deploy the model using Vertex AI.

Suggested Answer: B

AutoML Natural Language is a service that allows you to quickly build, test and deploy natural language processing (NLP) models without needing to have expertise in NLP or machine learning. You can use it to train a classifier on your corpus of written support cases, and then use the AutoML API to perform classification on new requests. Once the model is trained, it can be deployed as a REST API. This allows the classifier to be integrated into your pipeline and be easily consumed by other systems.

Get Premium Professional Machine Learning Engineer Questions as Interactive Web-Based Practice Test or PDF Real Exam Format Detailed Explanations Instant Access Get Your Practice Test

26 comments · newest first

Sherly 1 month ago

C is interesting, but I prefer a more straightforward approach.

Fernanda 1 month ago

D is powerful, but complex. Might take too long.

Jessenia 2 months ago

A seems quick, but lacks customization.

Brandon 2 months ago

I think B is the best choice. AutoML is user-friendly.

Daniel 2 months ago

D could be powerful, but more complex to set up.

Sharita 2 months ago

A seems simpler, but lacks customization.

Ammie 2 months ago

I agree, B is quick to deploy. Good for testing too.

Loreta 2 months ago

I think B is the best choice. AutoML is user-friendly.

Chan 3 months ago

C is interesting, but I feel it's more complex than needed.

Paz 3 months ago

A seems quick, but I doubt its accuracy.

Aretha 3 months ago

I prefer D. BERT is powerful for text classification.

Geraldo 3 months ago

I think B is the best option. AutoML is user-friendly.

Charlena 3 months ago

C seems outdated, why not use the latest tech like D?

Truman 4 months ago

Wait, can BigQuery ML really handle this well? Sounds too simple.

Dottie 5 months ago

A is too basic for this task, we need something more robust.

Cyril 5 months ago

I think D could give better accuracy with BERT.

Dorsey 5 months ago

B is the way to go! AutoML makes it easy.

Colette 6 months ago

C sounds interesting, but is logistic regression enough?

Serina 6 months ago

Wait, can AutoML really handle all that?

Felix 6 months ago

A seems too basic for this task.

Carmen 6 months ago

I think D could give better accuracy with BERT.

Evelynn 6 months ago

B is the best option for quick deployment!

Madelyn 6 months ago

I recall that BigQuery ML is great for quick models, but I wonder if logistic regression is powerful enough for classifying text like this.

Dorothy 7 months ago

I practiced a similar question where we had to choose between different ML tools. I feel like the Cloud Natural Language API might not give us enough customization for our needs.

Dominque 7 months ago

I'm not entirely sure, but I remember something about using BERT for text classification. It seems like a strong option, but it might be more complex to set up.

Lawrence 7 months ago

I think using AutoML Natural Language could be a good choice since it simplifies the process of building a classifier.

Google Professional Machine Learning Engineer Exam - Topic 4 Question 112 Discussion