Unsupervised event extraction

A system, comprising:

• a memory that stores computer executable components;
• a processor that executes the computer executable components stored in the memory, wherein the computer executable components comprise:
• an event extraction component that generates structured event schema defining different events represented in a corpus of unstructured text data using one or more unsupervised machine learning processes;
• and
• a query component that receives an unstructured text query and employs the structured event schema to identify one or more parts of the corpus of unstructured text data that are relevant to the unstructured text query based on a correspondence between reference structured event data associated with the one or more parts as defined in the structured event schema and structured event data generated for the unstructured text query by the event extraction component using the one or more unsupervised machine learning processes.

A method, comprising:

• generating, by a system operatively coupled to a processor, structured event schema defining different events represented in a corpus of unstructured text data using one or more unsupervised machine learning processes;
• receiving, by the system, unstructured text query;
• converting, by the system, the unstructured text query into structured event data using the one or more unsupervised machine learning processes;
• and
• identifying, by the system, one or more parts of the corpus of unstructured text data that are relevant to the unstructured text query based on a correspondence between reference structured event data associated with the one or more parts as defined in the structured event schema and the structured event data.