You have a custom named entity recognition (NER) project in Azure Language in Foundry Tools for support tickets. The schema for the project contains an entity type named ContactInfo.In tagged training files, ContactInfo is used for phone numbers, email addresses, and social media handles.Model evaluation shows low precision for ContactInfo, including false positives in which nearby text is extracted as ContactInfo.You need to improve the precision of the project.What should you do before retraining the model?
Answer(s): D
To improve the precision of the project before retraining the model, you should replace ContactInfo by usingPhone, Email, and SocialMedia entities, and then relabel every matching span.Reduces Model Confusion: Combining distinct types of data (like phone numbers, emails, and usernames) into a single generic entity (ContactInfo) creates conflicting patterns for the model. Splitting them allows the model to learn the specific, unique syntax rules of each type.Eliminates Over-extraction: When an entity is too broad, the model struggles to identify where the entity begins and ends, leading to false positives by grabbing adjacent text. Distinct entities provide sharper, cleaner boundaries.
https://learn.microsoft.com/en-us/azure/ai-services/language-service/custom-named-entity-recognition/overvie w
You are building a text-to-speech solution that uses Azure Speech in Foundry Tools to read instructions from the script in a text file.You discover that the solution often pronounces technical terms incorrectly.You need to prevent the incorrect pronunciations. The solution must minimize development effort.What should you do?
Answer(s): B
Using Speech Synthesis Markup Language (SSML) with the <phoneme> element is the ideal way to fix mispronunciations for technical terms.The <phoneme> tag lets you override the default text-to-speech model by explicitly defining the sounds using the International Phonetic Alphabet (IPA).
https://learn.microsoft.com/en-us/answers/questions/5729867/pronunciation-issue-when-generating-audio-fro m-ssm
HOTSPOT (Drag and Drop is not supported)You have a Python application that redacts sensitive information before sending prompt text to a language model. The application has the following code:For each of the following statements, select Yes if the statement is true. Otherwise, select No.Note: Each correct selection is worth one point.Hot Area:
Answer(s): A
Box 1: NoThe audit list will not include entity records for "Contact" and "SSN" because neither word is a target PII entity type defined in the configuration.The code limits scanning to Person and PhoneNumber via the piiCategories list."Contact" Definition: This is a regular English verb/noun, not a person's name or a telephone number."SSN" Definition: While "SSN" is a text label that points to sensitive data, it is a descriptor rather than an actualSocial Security Number.Box 2: YesFor the given sample_text, text_for_model will include both or john.doe@contoso.com and 859-98-0987completely unredacted.The payload explicitly restricts the Personally Identifiable Information (PII) recognition to only two specific categories by setting piiCategories: ["Person", "PhoneNumber"].Email Address Excluded: Because the Email category is omitted from the configuration list, the service bypasses the email address (john.doe@contoso.com) and leaves it fully intact.SSN Excluded: Similarly, because the USSSN (or equivalent Social Security Number) category is not specified in the piiCategories array, the SSN (859-98-0987) is completely ignored by the redaction policy and remains visible.Box 3: Yes text_for_model will contain entity type masks for "John Doe" and "312-555-1234", but only for those two specific items.The piiCategories array explicitly requests Person and PhoneNumber.Applied Redaction: The Azure AI Language service will replace "John Doe" and "312-555-1234" with masks like * or entity labels (depending on exact policy settings).Skipped Data: The email (john.doe@contoso.com) and the SSN (859-98-0987) will not be redacted because their categories (Email and USSSN) were omitted from your piiCategories list.
https://learn.microsoft.com/en-us/azure/ai-services/language-service/personally-identifiable-information/concep ts/conversations-entity-categories
DRAG DROP (Drag and Drop is not supported)You are developing an application that will detect faulty components produced on a factory production line. The components are specific to your business.You need to use the Azure Custom Vision API to help detect common faults.Which three actions should you perform in sequence? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order.Select and Place:
Step 1: Create a projectYou must first set up a new project in the Custom Vision portal or via the SDK to store your data and configuration.Step 2: Upload and tag imagesNext, you need to upload photos of your specific factory components and draw bounding boxes around the faults to tag them.Step 3: Train the object detection modelBecause you need to identify and locate specific, localizable faults on a component, you must train an object detection model rather than a general classifier model.
https://thegroundtruth.blog/tag/computervision/
You are developing a new sales system that will process user-generated video and text from a public-facing website.You plan to notify users that their data has been processed by the sales system.Which responsible AI principle does this help meet?
Notifying users that their data has been processed by your sales system fulfills the Transparency responsibleAI principle. Transparency ensures that users are informed about how their data is collected and processed,which helps foster understanding and build trust between users and technology providers.
https://learn.microsoft.com/en-us/microsoft-copilot-studio/guidance/responsible-ai
Post your Comments and Discuss Microsoft AI-103 exam prep with other Community members:
Our website is free, but we have to fight against AI bots and content theft. We're sorry for the inconvenience caused by these security measures. You can access the rest of the AI-103 content, but please register or login to continue.