Text analysis solutions · 10–15%

Language analysis & translation

~2 min read

Azure Language (Foundry Tools)

Azure Language is a Foundry Tool with prebuilt APIs for analyzing text: detecting its language, finding entities, and spotting personal data — no model prompting needed.

Client: TextAnalyticsClient (azure-ai-textanalytics), key or Entra ID auth.

FeatureMethodNotes
Language detectiondetect_language()Confidence 0–1; mixed-language text returns the dominant language with a lower score; unparseable text returns (unknown) with score 0. Doc ≤ 5,120 chars, ≤1,000 docs/request
Named Entity Recognitionrecognize_entities()Person, Location, DateTime, Organization, Address, Email, URL…
PII detection + redactionrecognize_pii_entities()Categories like USSocialSecurityNumber; doc.redacted_text = masked with *

Sentiment, summarization, key phrases exist but flagged deprecated/legacy in current content — modern route = generative prompting.

LLM-based text analysis

Study guide expects: entities/topics/summaries/structured JSON output via generative prompting (Responses API + JSON format instruction or structured outputs), sentiment/tone/safety detection with prompts, domain customization (compliance summarization) via prompt engineering or fine-tuning.

“Redact SSNs from transcripts” means Azure Language PII, not an LLM. “Extract custom domain fields as JSON” means LLM structured output. A specialized deterministic task points to a Foundry Tool; an open-ended one points to an LLM.

Azure Translator

Azure Translator is a neural machine-translation service in Foundry Tools.

Translate = change language. Transliterate = change script only. Exam loves this pair.