Question 4
Domain 4: Implement Natural Language Processing SolutionsA healthcare system needs to scan patient records and automatically remove patient names, dates of birth, and social security numbers before the records are used for AI model training. Which Azure AI Language feature should you use?
Correct answer: C
Explanation
PII Detection identifies personally identifiable information such as names, dates of birth, and social security numbers in text. The text redaction option then removes or masks that data before the records are used for training, which matches the need to automatically sanitize patient records.
Why each option is right or wrong
A. Named Entity Recognition (NER)
B. Key Phrase Extraction
C. PII Detection with text redaction
Azure AI Language’s PII Detection is the feature designed to identify personally identifiable information in unstructured text, including person names, dates of birth, and U.S. Social Security numbers. The text redaction capability then masks or removes the detected entities from the document, which is the required preprocessing step before using the records for model training.
D. Sentiment Analysis with opinion mining