Table of Contents
Which NLP workloads are needed to translate and categorize books by topic?
Ace the AI-900 exam by understanding which natural language processing (NLP) workloads are used to solve complex problems. Learn why translation and key phrase extraction are the correct combination for a solution that reads books in different languages and categorizes them by topic.
Question
You have a solution that reads books in different languages and categorizes the books based on topic. Which types of natural language processing (NLP) workloads does the solution use?
A. Translation and sentiment analysis
B. Translation and key phrase extraction
C. Speech recognition and entity recognition
D. Speech recognition and language modeling
Answer
B. Translation and key phrase extraction
Explanation
The correct types of natural language processing (NLP) workloads are B. Translation and key phrase extraction. The solution described involves a two-step process, and each step maps directly to one of these workloads.
Analyzing the Two-Step Process
The problem requires the AI solution to perform two distinct tasks on the text from the books:
- Handling Multiple Languages: The scenario specifies that the solution “reads books in different languages.” To process this text consistently for categorization, the system must first understand it, regardless of the source language. This requires the translation workload to convert the text from various languages into a single, common language for analysis.
- Categorizing by Topic: The second task is to “categorize the books based on topic.” To determine a book’s topic, the system needs to identify the main subjects, themes, and important concepts within the text. This is the primary function of the key phrase extraction workload, which identifies and pulls out the most significant terms and phrases. These extracted key phrases (e.g., “quantum mechanics,” “Roman Empire,” “Impressionist art”) directly inform the topic categorization.
Why Other Options Are Incorrect
- Translation and sentiment analysis: Sentiment analysis determines the emotional tone (positive, negative, neutral) of a text. This does not help in identifying the subject matter or topic of a book.
- Speech recognition and entity recognition: Speech recognition is used to convert spoken audio into text. The scenario describes a solution that “reads books,” which implies text input, making speech recognition irrelevant.
- Speech recognition and language modeling: As with the previous option, speech recognition is not applicable here. While language modeling is a foundational technology for NLP, key phrase extraction is the specific workload that directly addresses the task of identifying topics.
Microsoft Azure AI Fundamentals AI-900 certification exam practice question and answer (Q&A) dump with detail explanation and reference available free, helpful to pass the Microsoft Azure AI Fundamentals AI-900 exam and earn Microsoft Azure AI Fundamentals AI-900 certification.