Implement knowledge mining and information extraction solutions →hardMultiple ChoiceObjective-mapped

AI-102 Practice Question: Implement knowledge mining and information extraction solutions

Exhibit

{
  "skillset": {
    "skills": [
      {
        "@odata.type": "#Microsoft.Skills.Text.SplitSkill",
        "name": "split",
        "context": "/document",
        "textSplitMode": "pages",
        "maximumPageLength": 5000,
        "pageOverlapLength": 500,
        "defaultLanguageCode": "en",
        "inputs": [
          { "name": "text", "source": "/document/content" }
        ],
        "outputs": [
          { "name": "textItems", "targetName": "pages" }
        ]
      },
      {
        "@odata.type": "#Microsoft.Skills.Text.V3.SentimentSkill",
        "name": "sentiment",
        "context": "/document/pages/*",
        "defaultLanguageCode": "en",
        "inputs": [
          { "name": "text", "source": "/document/pages/*" }
        ],
        "outputs": [
          { "name": "sentiment", "targetName": "sentimentLabel" },
          { "name": "confidenceScores", "targetName": "confidenceScores" }
        ]
      }
    ]
  }
}

Refer to the exhibit. You are using Azure AI Search with a skillset that splits documents into pages and then analyzes sentiment per page. You notice that the sentiment analysis is returning unexpected results, such as positive sentiment for negative content. What is the most likely cause?

Answer choices

Why each option matters

Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.

Correct answer & explanation

✓

The page split mode with overlap may still cut sentences, causing sentiment to be evaluated on incomplete sentences.

The SplitSkill uses 'pages' mode which often splits at page boundaries, potentially cutting sentences in half. This can cause the sentiment analysis to receive incomplete text, leading to incorrect sentiment. Option A is not the primary issue. Option B is about the initial text, not splitting. Option C is about the split context, but the sentiment context is correct.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

✗
The SentimentSkill is receiving the entire document text instead of individual pages.
Why it's wrong here
The context is set to '/document/pages/*', so it receives each page.
✗
The split skill context '/document' should be '/document/content'.
Why it's wrong here
The context '/document' is correct for splitting the entire document content.
✗
The defaultLanguageCode is set to 'en' but the documents contain other languages.
Why it's wrong here
While mixed languages could cause issues, the primary problem is the splitting.
✓
The page split mode with overlap may still cut sentences, causing sentiment to be evaluated on incomplete sentences.
Why this is correct
Splitting at page boundaries can break sentences, leading to inaccurate sentiment analysis.

Go deeper

AI-102 Practice Question: Implement knowledge mining and information extraction solutions

Exhibit

Why each option matters

Option-by-option breakdown

Related to this question