A simple but tough-to-beat baseline for the Fake News Challenge stance detection task
Open paper
Benchmark
Model
Rank
Results
fake-news-detection-on-fnc-1
3rd place at FNC-1 - Team UCL Machine Reading (Riedel et al., 2017)
#4
Weighted Accuracy: 81.72
Per-class Accuracy (Unrelated): 97.90
…
Rank counts only results with a code link.