Unsupervised Question Answering for Fact-Checking
This addresses fact-checking for information verification, but it is incremental as it adapts existing methods to a new task.
The paper tackles fact-checking by transforming the FEVER dataset into a Cloze-task using masked named entities and employing BERT for unsupervised question answering, achieving label accuracies of 80.2% on the development set and 80.25% on the test set.
Recent Deep Learning (DL) models have succeeded in achieving human-level accuracy on various natural language tasks such as question-answering, natural language inference (NLI), and textual entailment. These tasks not only require the contextual knowledge but also the reasoning abilities to be solved efficiently. In this paper, we propose an unsupervised question-answering based approach for a similar task, fact-checking. We transform the FEVER dataset into a Cloze-task by masking named entities provided in the claims. To predict the answer token, we utilize pre-trained Bidirectional Encoder Representations from Transformers (BERT). The classifier computes label based on the correctly answered questions and a threshold. Currently, the classifier is able to classify the claims as "SUPPORTS" and "MANUAL_REVIEW". This approach achieves a label accuracy of 80.2% on the development set and 80.25% on the test set of the transformed dataset.