CODEWITHSUNDEEP
pythonwikipediainformation-retrieval
Samreen Ahmad Kazi
Samreen Ahmad Kazi

Reputation: 13

What is methodology behind retrieving k most relevant articles using Wikipedia Python library?

Does the Wikipedia python library automatically retrieve the most relevant k documents based on given query? What is the underlying structure of retrieving those documents? Does it use TF-IDF or any other approach?

Upvotes: 0

Views: 72

Answers (1)

IonicSolutions
IonicSolutions

Reputation: 2599

As you can see from the module's source code, wikipedia queries the Wikipedia API and returns its results. The order of documents returned is therefore determined by Wikipedia's own CirrusSearch, which is built on Elasticsearch. You can find more information in the Wikipedia API documentation.

Upvotes: 1

Related Questions