Truth Discovery with Memory Network

TL;DR

This paper introduces memory network models for truth discovery that consider both source reliability and the mutual credibility among statements about the same object, significantly improving accuracy over existing methods.

Contribution

The paper proposes novel memory network based models that incorporate mutual effects among statement credibilities and adaptively weight different data types for enhanced truth discovery.

Findings

Memory network models outperform state-of-the-art methods.

Models effectively learn source reliability and statement credibility.

Adaptive weighting improves truth prediction accuracy.

Abstract

Truth discovery is to resolve conflicts and find the truth from multiple-source statements. Conventional methods mostly research based on the mutual effect between the reliability of sources and the credibility of statements, however, pay no attention to the mutual effect among the credibility of statements about the same object. We propose memory network based models to incorporate these two ideas to do the truth discovery. We use feedforward memory network and feedback memory network to learn the representation of the credibility of statements which are about the same object. Specially, we adopt memory mechanism to learn source reliability and use it through truth prediction. During learning models, we use multiple types of data (categorical data and continuous data) by assigning different weights automatically in the loss function based on their own effect on truth discovery prediction. The experiment results show that the memory network based models much outperform the state-of-the-art method and other baseline methods.