Automatic Stance Detection Using End-to-End Memory Networks
Computation and Language
2018-04-23 v1
Abstract
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.
Cite
@article{arxiv.1804.07581,
title = {Automatic Stance Detection Using End-to-End Memory Networks},
author = {Mitra Mohtarami and Ramy Baly and James Glass and Preslav Nakov and Lluis Marquez and Alessandro Moschitti},
journal= {arXiv preprint arXiv:1804.07581},
year = {2018}
}
Comments
NAACL-2018; Stance detection; Fact-Checking; Veracity; Memory networks; Neural Networks; Distributed Representations