Artificial intelligence for identifying relevant content related to specific tasks

A system for identifying content in a natural language input, comprising:

• a memory for storing executable program code;
• and
• one or more processors, functionally coupled to the memory, the one or more processors being responsive to computer-executable instructions contained in the program code and operative to:
• receive the natural language input, the natural language input comprising a plurality of sentences in a productivity application document;
• identify a task type associated with the natural language input;
• apply a machine learning model to the natural language input, wherein the machine learning model has been trained to rank sentences based on their relevance to the identified task type, the machine learning model comprising:
• an embedding layer, the embedding layer generating an embedding for each word in the natural language input;
• a distinct sentence aggregation layer, the distinct sentence aggregation layer aggregating the embeddings for each word in the natural language input into a distinct embedding for each of the plurality of sentences;
• a contextual aggregation layer, the contextual aggregation layer aggregating each distinct embedding for each of the plurality of sentences into a contextual embedding for each of the plurality of sentences;
• and
• a scoring layer, the scoring layer ranking each of the plurality of sentences based on their relevance to the schedule meeting task.

A computer-readable storage device comprising executable instructions that, when executed by one or more processors, assists with identifying relevant content in a natural language input, the computer-readable storage device including instructions executable by the one or more processors for:

• receiving the natural language input, the natural language input comprising a plurality of sentences in an email;
• applying a machine learning model to the natural language input, wherein the machine learning model has been trained to rank sentences based on their relevance to a schedule meeting task, the machine learning model comprising:
• an embedding layer, the embedding layer generating an embedding for each word in the natural language input;
• a distinct sentence aggregation layer, the distinct sentence aggregation layer aggregating the embeddings for each word in the natural language input into a distinct embedding for each of the plurality of sentences;
• a contextual aggregation layer, the contextual aggregation layer aggregating each distinct embedding for each of the plurality of sentences into a contextual embedding for each of the plurality of sentences;
• and
• a scoring layer, the scoring layer ranking each of the plurality of sentences based on their relevance to the schedule meeting task.