|
| 1 | +### YamlMime:ModuleUnit |
| 2 | +uid: learn.wwl.build-rag-applications-azure-database-postgresql.knowledge-check |
| 3 | +title: Module assessment |
| 4 | +metadata: |
| 5 | + title: Module assessment |
| 6 | + description: "Knowledge check" |
| 7 | + ms.date: 09/15/2025 |
| 8 | + author: wwlpublish |
| 9 | + ms.author: calopez |
| 10 | + ms.topic: unit |
| 11 | +durationInMinutes: 5 |
| 12 | +quiz: |
| 13 | + title: Check your knowledge |
| 14 | + questions: |
| 15 | + - content: A hospital stores long notes from doctors and wants a way to highlight the key sentences without altering the wording. Which technique should be used? |
| 16 | + choices: |
| 17 | + - content: Abstractive summarization |
| 18 | + isCorrect: false |
| 19 | + explanation: Incorrect. Abstractive summarization rephrases text instead of keeping sentences intact. |
| 20 | + - content: Extractive summarization |
| 21 | + isCorrect: true |
| 22 | + explanation: Correct. Extractive summarization surfaces the most important sentences as written:contentReference[oaicite:0]{index=0}. |
| 23 | + - content: Key phrase extraction |
| 24 | + isCorrect: false |
| 25 | + explanation: Incorrect. Key phrase extraction pulls out important concepts, not full sentences. |
| 26 | + - content: A healthcare provider wants to predict patient no-shows by automatically building models without manual tuning. Which feature would help? |
| 27 | + choices: |
| 28 | + - content: Automated Machine Learning (AutoML) |
| 29 | + isCorrect: true |
| 30 | + explanation: Correct. AutoML automates model selection, feature engineering, and hyperparameter tuning:contentReference[oaicite:8]{index=8}. |
| 31 | + - content: Opinion mining |
| 32 | + isCorrect: false |
| 33 | + explanation: Incorrect. Opinion mining analyzes aspects of text, not predictive models. |
| 34 | + - content: Manual model training |
| 35 | + isCorrect: false |
| 36 | + explanation: Incorrect. Manual training requires expert selection and tuning, which is what AutoML removes. |
| 37 | + - content: A ride-sharing company wants to know why some feedback is mixed, such as "The driver was friendly but the car was dirty." What technique would help? |
| 38 | + choices: |
| 39 | + - content: Opinion mining |
| 40 | + isCorrect: true |
| 41 | + explanation: Correct. Opinion mining links sentiment to aspects such as driver and car:contentReference[oaicite:1]{index=1}. |
| 42 | + - content: Sentiment analysis |
| 43 | + isCorrect: false |
| 44 | + explanation: Incorrect. Sentiment analysis gives an overall tone but doesn't separate aspects. |
| 45 | + - content: Named entity recognition |
| 46 | + isCorrect: false |
| 47 | + explanation: Incorrect. Entity recognition identifies terms like "driver" or "car" but doesn't classify opinions about them. |
0 commit comments