A General Framework for Multiple Choice Question Answering Based on Mutual Information and Reinforced Co-occurrence Chapter uri icon


  • As a consequence of the ever-increasing volume of available data, scanning and querying textual documentation in pursuit of particular facts is a tedious process compounded by a situation in which data representation very often does not fulfill client needs. To address these ever-increasing requirements, we have developed a system based on the idea of shared knowledge to get an innovative and smart approach for the automatic response to multiple-choice questions. An experimental assessment of a variety of general-purpose reference datasets appears to suggest that such an approach is plausible.

publication date

  • January 1, 2019