Automatic Stance Detection Using End-to-End Memory Networks

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... (read more)

PDF Abstract NAACL 2018 PDF NAACL 2018 Abstract
No code implementations yet. Submit your code now

Datasets


Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Fake News Detection FNC-1 Neural method from Mohtarami et al. + TF-IDF (Mohtarami et al., 2018) Weighted Accuracy 81.23 # 4
Fake News Detection FNC-1 Neural method from Mohtarami et al. (Mohtarami et al., 2018) Weighted Accuracy 78.97 # 5

Methods used in the Paper


METHOD TYPE
Softmax
Output Functions
End-To-End Memory Network
Working Memory Models
Memory Network
Working Memory Models