Analyzing natural language questions to determine missing information in order to improve accuracy of answers

US9965548B2 · kind B2 · utility

Assignee

• International Business Machines Corporation · US

Inventors

• Peter F. Haggar · Raleigh, US
• Dane A. Johnson · Townsend, US
• Mark G. Megerian · Rochester, US
• John E. Petri · Rochester, US
• Stephan J. Roorda · Fuquay-Varina, US
• Leah R. Smutzer · Rochester, US
• Richard J. Stevens · Vergennes, US
• Richard L. Stillwell · Austin, US

Key dates

• Filing date: Dec 5, 2013
• Grant date: May 8, 2018
• Expiry date: Aug 28, 2034

Classification

• Technology area (CPC G): Physics
• CPC primary: G09B5/02
• WIPO field: Control
• WIPO sector: Instruments

Abstract

A mechanism is provided in a data processing system comprising a processor and a memory configured to implement a question and answer system (QA), for improving answers to an input question. An input question is received and parsed for a known set of critical information required to answer the input question. Responsive to one or more pieces of critical information failing to be identifiable in the input question, a user who submitted the input question is prompted for the one or more pieces of critical information via a graphical user interface (GUI).