Automatic Stance Detection Using End-to-End Memory Networks
This addresses the problem of automated stance detection for fake news analysis, but it is incremental as it builds on existing memory network and neural network techniques.
The paper tackled stance detection by predicting agreement, disagreement, discussion, or unrelatedness to a claim and extracting evidence snippets, achieving state-of-the-art performance on the Fake News Challenge dataset.
We present a novel end-to-end memory network for stance detection, which jointly (i) predicts whether a document agrees, disagrees, discusses or is unrelated with respect to a given target claim, and also (ii) extracts snippets of evidence for that prediction. The network operates at the paragraph level and integrates convolutional and recurrent neural networks, as well as a similarity matrix as part of the overall architecture. The experimental evaluation on the Fake News Challenge dataset shows state-of-the-art performance.