Topic 1 — Question Set 1

You have 100 chatbots that each has its own Language Understanding model. Frequently, you must add the same phrases to each model. You need to programmatically update the Language Understanding models to include the new phrases. In the following code snippet, choose the method that should replace the first blank: var phraselistId = await client.Features.[blank] (appId, versionId, new [blank] { EnabledForAllModels = false, IsExchangeable = true, Name = "PL1", Phrases = "item1,item2,item3,item4,item5" });

• AddPhraseListAsync

• SavePhraselistAsync

• UploadPhraseListAsync

• Phrases

Using the same scenario and code, choose the object type that should replace the second blank in the following snippet: var ph Macro: var phraselistId = await client.Features.[method] (appId, versionId, new [blank] { EnabledForAllModels = false, IsExchangeable = true, Name = "PL1", Phrases = "item1,item2,item3,item4,item5" });

• PhraselistCreateObject

• Phraselist

• Phrases

• UploadPhraseListAsync

You plan to use a Language Understanding application named app1 that is deployed to a container. App1 was developed by using a Language Understanding authoring resource named lu1. App1 has versions shown in the table: Version — Trained date — Published date; v1.2 — None — None; v1.1 — 2020-10-01 — None; v1.0 — 2020-09-01 — 2020-09-15. You need to create a container that uses the latest deployable version of app1. Select the first action you should perform from the following actions: Run a container that has version set as an environment variable; Export the model by using the Export as JSON option; Select v1.1 of app1; Run a container and mount the model file; Select v1.0 of app1; Export the model by using the Export for containers (GZIP) option; Select v1.2 of app1.

• Select v1.2 of app1

• Select v1.1 of app1

• Select v1.0 of app1

• Export the model by using the Export as JSON option

• Run a container that has version set as an environment variable

Using the same scenario and actions list, after selecting the latest deployable version of app1, choose the next action to prepare the model for running in a container. Actions: Run a container that has version set as an environment variable; Export the model by using the Export as JSON option; Run a container and mount the model file; Export the model by using the Export for containers (GZIP) option.

• Export the model by using the Export for containers (GZIP) option

• Export the model by using the Export as JSON option

• Run a container that has version set as an environment variable

• Run a container and mount the model file

Continuing the sequence for creating a container that uses the latest deployable version of app1, select the final action to run the model after exporting the correct package. Actions: Run a container and mount the model file; Run a container that has version set as an environment variable; Select v1.0 of app1.

• Run a container and mount the model file

• Run a container that has version set as an environment variable

• Select v1.0 of app1

You need to build a chatbot that meets the following requirements: • Supports chit-chat, knowledge base, and multilingual models • Performs sentiment analysis on user messages • Selects the best language model automatically What should you integrate into the chatbot?

• QnA Maker, Language Understanding, and Dispatch

• Translator, Speech, and Dispatch

• Language Understanding, Text Analytics, and QnA Maker

• Text Analytics, Translator, and Dispatch

Your company wants to reduce how long it takes for employees to log receipts in expense reports. All the receipts are in English. You need to extract top-level information from the receipts, such as the vendor and the transaction total. The solution must minimize development effort. Which Azure service should you use?

• Custom Vision

• Personalizer

• Form Recognizer

• Computer Vision

You need to create a new resource that will be used to perform sentiment analysis and optical character recognition (OCR). The solution must use a single key and endpoint to access multiple services, consolidate billing for future services, and support the use of Computer Vision in the future. In the HTTP request shown in the diagram, which HTTP method should you use to create the resource? Each correct selection is worth one point.

• PATCH

• POST

• PUT

You need to create a new resource that will be used to perform sentiment analysis and optical character recognition (OCR). The solution must use a single key and endpoint to access multiple services, consolidate billing for future services, and support the use of Computer Vision in the future. In the HTTP request shown in the diagram, which value should you select for the kind field to meet these requirements? Each correct selection is worth one point.

• CognitiveServices

• ComputerVision

• TextAnalytics

You are developing a new sales system that will process the video and text from a public-facing website. You plan to monitor the sales system to ensure that it provides equitable results regardless of the user's location or background. Which two responsible AI principles provide guidance to meet the monitoring requirements? Each correct answer presents part of the solution. NOTE: Each correct selection is worth one point.

• transparency

• fairness

• inclusiveness

• reliability and safety

• privacy and security