Paper 4

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

Authors: Jorge Martinez-Gil, Bernhard Freudenthaler, A Min Tjoa

Volume 42 (2019)

Abstract

As a result of the continuously growing volume of information available, browsing and querying of textual information in search of specific facts is currently a tedious task exacerbated by a reality where data presentation very often does not meet the needs of users. To satisfy these ever-increasing needs, we have designed an solution to provide an adaptive and intelligent solution for the automatic answer of multiple-choice questions based on the concept of mutual information. An empirical evaluation over a number of general-purpose benchmark datasets seems to indicate that this solution is promising.