Microsoft Azure AI Fundamentals (AI-900)Describe features of Natural Language Processing (NLP) workloads on AzureHard
A legal firm needs to process thousands of contracts to identify specific clauses, dates, and parties involved, even if they are phrased uniquely across different documents. The firm has a clear definition of what constitutes a 'clause start', 'party name', or 'effective date'. They need to extract these precisely defined elements. Which Azure AI NLP capability is most effective for this highly specialized information extraction task?
- ACustom Named Entity Recognition (Custom NER)
- BKey Phrase Extraction
- CText Summarization
- DGeneric Named Entity Recognition (NER)
Show answer & explanationAnswer & explanation
Correct answer: A. Custom Named Entity Recognition (Custom NER)
While generic NER can extract common entities, the need to identify 'specific clauses', 'clause start', 'party name', or 'effective date' which are unique to legal documents and require precise definition points to Custom Named Entity Recognition. Custom NER allows the firm to define and train models for entities specific to their domain.
Why the other options are wrong
- B. Key Phrase Extraction identifies important phrases, but doesn't classify them into structured custom entities.
- C. Text Summarization condenses text, not extracts specific custom entities.
- D. Generic NER extracts common entities like people, organizations, locations, but not highly specific legal concepts like 'clause start' or 'effective date'.
Custom Named Entity Recognition (Custom NER)
An advanced NLP capability that enables users to define and extract entities specific to their industry, domain, or use case, beyond the standard predefined entity types.
- Requires labeled data for training.
- Highly accurate for domain-specific entity extraction.
- Ideal for specialized document processing (e.g., legal, medical).
Memory trick: Custom NER Culls Crucial Contract Data