# Unsupervised Question Answering for Fact-Checking

arXiv: https://arxiv.org/abs/1910.07154 · HTML: https://mlsanity.com/paper/1910.07154/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Oct 2019.

## Built on by (most cited first, 3 of 3)

- [Identifying and Characterizing Active Citizens who Refute Misinformation in Social Media](https://mlsanity.com/paper/2204.10080/) (2022)
- [Unsupervised Pretraining for Fact Verification by Language Model Distillation](https://mlsanity.com/paper/2309.16540/) (2023)
- [TabVer: Tabular Fact Verification with Natural Logic](https://mlsanity.com/paper/2411.01093/) (2024)

## Abstract (arXiv)

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.