Microsoft Azure AI Fundamentals (AI-900)Describe features of Natural Language Processing (NLP) workloads on AzureHard
A legal firm needs to process thousands of legal documents to extract specific clauses, dates, and party names that are unique to their domain and not typically found in general NLP models. Which Azure Cognitive Service for Language feature allows them to train a model to recognize these highly specialized entities?
- APrebuilt Named Entity Recognition
- BKey Phrase Extraction
- CCustom Named Entity Recognition
- DText Summarization
Show answer & explanationAnswer & explanation
Correct answer: C. Custom Named Entity Recognition
While prebuilt NER can identify common entities, the scenario specifies unique, domain-specific entities (specific clauses, dates, party names in legal context). Custom Named Entity Recognition allows the firm to train a model with their own labeled data to accurately identify these specialized entities.
Why the other options are wrong
- A. Prebuilt NER identifies common entities but would likely miss highly specialized legal terms.
- B. Key Phrase Extraction identifies general topics, not specific structured entities.
- D. Text Summarization condenses text, it doesn't extract specific entity types.
Custom Named Entity Recognition
Custom Named Entity Recognition is an NLP capability that enables users to train models to identify and categorize specific, domain-specific entities from text, beyond what pre-trained models can offer.
- Requires labeled training data relevant to the custom entities.
- Essential for specialized industries like legal, medical, finance.
- Part of Azure Cognitive Service for Language's custom features.
Memory trick: Custom Entities Need Custom Recognition.