Bi-LSTM (max-pooling, attention)

Reported on 5 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing5 results

Fake News DetectiononFNC-1
Per-class Accuracy (Agree)· 2018-11-02
51.34
best: 88.47 (ZAINAB A. JAWAD, AHMED J. OBAID (CNN and DNN with SCM, 2022))
SOTA
Combining Similarity Features and Deep Representation Learning for Stance Detection in the Context of Checking Fake News arXiv:1811.00706
Fake News DetectiononFNC-1
Per-class Accuracy (Disagree)· 2018-11-02
10.33
best: 96 (ZAINAB A. JAWAD, AHMED J. OBAID (CNN and DNN with SCM, 2022))
SOTA
Combining Similarity Features and Deep Representation Learning for Stance Detection in the Context of Checking Fake News arXiv:1811.00706
Fake News DetectiononFNC-1
Per-class Accuracy (Discuss)· 2018-11-02
81.52
best: 87.7 (ZAINAB A. JAWAD, AHMED J. OBAID (CNN and DNN with SCM, 2022))
Combining Similarity Features and Deep Representation Learning for Stance Detection in the Context of Checking Fake News arXiv:1811.00706
Fake News DetectiononFNC-1
Per-class Accuracy (Unrelated)· 2018-11-02
96.74
best: 99.36 (Sepúlveda-Torres R., Vicente M., Saquete E., Lloret E., Palomar M. (2021))
Combining Similarity Features and Deep Representation Learning for Stance Detection in the Context of Checking Fake News arXiv:1811.00706
Fake News DetectiononFNC-1
Weighted Accuracy· 2018-11-02
82.23
best: 90.73 (Sepúlveda-Torres R., Vicente M., Saquete E., Lloret E., Palomar M. (2021))
Combining Similarity Features and Deep Representation Learning for Stance Detection in the Context of Checking Fake News arXiv:1811.00706