Task Recognition

This demo showcases a hybrid method that leverages a Deep Learning classifier and heuristic rules to identify requests that place an obligation on a recipient, usually within the context of textual conversations. If a sentence is identified as task, the Task Annotator generates the following information:

  • Actions: Generates a list of possible actions predicted as necessary to address a request. Considering the context of mobile applications, these actions can include writing back an email, making a call or opening your calendar.
  • Priority: Generates a label indicating the urgency of a task as inferred from date expressions or priority patterns identified in a sentence.

Examples:

“Hello John, this is a reminder of the company's Christmas party. Please confirm your assistance within the next two weeks.”

“Hi, we need to finish the templates this week. Send me your changes as soon as you can. Also let me know your available times for the meeting before the end of the next week.”