data mining - find all two word phrases that appear in more than one row in a dataset

Question

We would like to run a query that returns two word phrases that appear in more than one row. So for e.g. take the string "Data Ninja". Since it appears in more than one row in our dataset, the query should return that. The query should find all such phrases from all the rows in our dataset, by querying for two adjacent word combination (forming a phrase) in the rows that are in the dataset. These two adjacent word combinations should come from the dataset we loaded into BigQuery

How can we write this query in Google BigQuery?

The dataset is simply a long list of English sentences.

Answer 1

Waitting for answers