Describe features of Natural Language Processing workloads on Azure →hardMultiple ChoiceObjective-mapped
AI-900 Practice Question: Describe features of Natural Language Processing workloads on Azure
What is 'word sense disambiguation' (WSD) and why is it challenging for NLP?
⚠ Common exam trap
It's easy for candidates to confuse WSD with related but distinct NLP tasks like homophone correction (A) or machine translation (C), because all involve handling ambiguous words, but WSD specifically targets meaning selection within a single language based on context.
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
✓
Determining which meaning of an ambiguous word is intended based on surrounding context
Word sense disambiguation (WSD) is the NLP task of identifying which specific meaning of a polysemous word (a word with multiple meanings) is intended in a given context, using surrounding words, syntax, and semantic cues. This is challenging because many words have multiple, often unrelated meanings (e.g., 'bank' as a financial institution vs. river bank), and the correct sense depends on subtle contextual signals that are difficult for models to capture without deep understanding of the domain or world knowledge.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Correcting spelling mistakes caused by homophones (words that sound the same)
Why it's wrong here
Correcting spelling mistakes caused by homophones is the domain of spell-checking or grammar correction, not WSD. Homophones like 'their' and 'there' are different lexemes that happen to sound alike; a misspelling involves replacing one word form with another, whereas WSD handles a single word with multiple related or unrelated senses depending on context. For instance, deciding whether 'bank' means 'a place for money' or 'a river edge' does not involve correcting any spelling—the word form remains unchanged. Therefore, this option describes a surface-level orthographic fix, not the semantic disambiguation that WSD performs.
- ✓
Determining which meaning of an ambiguous word is intended based on surrounding context
Why this is correct
Determining which meaning of an ambiguous word is intended based on surrounding context is precisely word sense disambiguation. In WSD, a polysemous word like 'bank' is assigned the correct sense—such as 'financial institution' versus 'riverbank'—using features from the surrounding words, syntactic structure, and discourse. The task is to resolve lexical ambiguity by choosing a sense from a predefined sense inventory that fits the specific usage. This definition focuses on contextual inference, distinguishing WSD from language translation, dictionary sense counting, and spelling correction.
- ✗
Translating words from one language to their exact equivalent in another language
Why it's wrong here
Translating words from one language to their exact equivalent in another language describes machine translation, a distinct NLP task that involves mapping text between languages while preserving meaning. Although a translation system may internally rely on word sense disambiguation to choose the right target word, the overall process of cross-lingual transfer is not WSD itself. Unlike WSD, which operates within a single language, translation introduces source and target language complexities, and the notion of an 'exact equivalent' often fails due to polysemy and cultural differences.
- ✗
Measuring how many distinct meanings a word has across a dictionary
Why it's wrong here
Measuring how many distinct meanings a word has across a dictionary is a lexicographic activity: it involves counting or cataloging sense entries in a reference work. WSD does not aim to quantify a word's senses in isolation; rather, it takes a specific occurrence of a word in a sentence or discourse and selects which sense from an existing inventory applies. The output of WSD is a sense label for a token, not a numeric count of a word's possible senses. Thus, this option confuses the static resource (dictionary) with the dynamic task of contextual interpretation.
Go deeper
Related to this question
About these practice questions
Courseiva writes every AI-900 question from scratch — 985 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This AI-900 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI-900 exam.