fake news detectiontransfer learningfine-tuningTransformer models, trained and publicly released over the lasc couple of years, have proved effective in many NLP tasks. We wished to test their usefulness in particular on the stance detection task. We performed experiments on the data from the Fake...
Stance Detection dataset for FNC-1 For details of the task, see FakeNewsChallenge.org The data provided is (headline, body, stance) instances, where stance is one of {unrelated, discuss, agree, disagree}. The dataset is provided as two CSVs: train_bodies.csv This file contains the body ...
@article{riedel2017fnc, author = {Benjamin~Riedel and Isabelle~Augenstein and Georgios~P.~Spithourakis and Sebastian~Riedel}, title = {A simple but tough-to-beat baseline for the {Fake News Challenge} stance detection task}, journal = {CoRR}, volume = {abs/1707.03264}, year = {2017},...