Member-only story

Semantic search

A brief post on semantics, search, and semantic search

Ane Berasategi
Towards Data Science
5 min readMar 31, 2019

--

Photo by Kayla Farmer on Unsplash

⚠️ READ THE ORIGINAL POST IN MY BLOG ⚠️

Semantics is a branch of linguistics studying the meanings of words, their symbolic use, also including their multiple meanings.

“One morning I shot an elephant in my pajamas. How he got into my pajamas I’ll never know.” Groucho Marx

This sentence is semantically ambiguous: it’s not clear if the author shoots an elephant while in his pajamas, or if he shot the elephant, which happened to be in his pajamas. Clearly, in this example only one of the two makes sense, but both cases are gramatically correct.

“John and Mary are married.” (To each other? or separately?)

“John kissed his wife, and so did Sam”. (Sam kissed John’s wife or his own?)

More information on linguistic ambiguity.

Lexical search engines

At first, search engines (Google, Bing, DuckDuckGo, Yahoo, etc.) were lexical: the search engine looked for literal matches of the query words, without understanding of the query’s meaning and only returning links that contained the exact query.

--

--

Towards Data Science
Towards Data Science

Published in Towards Data Science

Your home for data science and AI. The world’s leading publication for data science, data analytics, data engineering, machine learning, and artificial intelligence professionals.

Responses (2)