A software company's internal help-center has thousands of articles. Employees often type questions in their own words, such as how do I get my money back, and expect the system to return the refund-policy article even though that article never contains the word money or back. Which capability should the search feature rely on?
Select an answer to reveal the explanation.
Short Explanation
The tricky part of this scenario is that the employee's words and the article's words barely overlap, yet the two are clearly about the same thing. A system that just matches literal keywords would miss that connection entirely, because it is comparing spelling, not meaning. What is needed instead is a way to represent both the question and every article as points in a kind of meaning-space, so that things that mean similar things end up near each other even when the vocabulary is completely different. That is what lets a phrase like getting money back land right next to an article that only ever talks about refunds. Extracting text from a scanned image is a different problem altogether and would not help match a typed question to existing articles. And judging whether a passage sounds upbeat or negative tells you nothing about which article answers the question. Since the whole challenge here is bridging different wording that shares the same underlying intent, the meaning-based matching approach is what actually closes that gap.
Full Explanation
The correct answer is C. Semantic search using vector embeddings converts both the employee's question and each article into numeric representations that capture meaning rather than exact wording, so a query like how do I get my money back can be matched to a refund-policy article based on conceptual similarity even without shared keywords. Option A is incorrect because keyword-based full-text search matches literal words and phrases between the query and the documents, so it would fail here precisely because the query and the article do not share the words money or back. Option B is incorrect because optical character recognition extracts text from images or scanned pages, which is unrelated to matching a typed question to the right article by meaning. Option D is incorrect because sentiment analysis measures the emotional tone of a passage, such as whether it sounds positive or negative, and has no mechanism for retrieving a relevant document based on what a query is asking about. Because the scenario hinges on returning results connected by meaning rather than shared vocabulary, the embedding-based semantic approach is the capability that solves the mismatch between how employees phrase questions and how articles are worded.