Unsupervised Question Answering for Fact-Checking

10/16/2019
by   Mayank Jobanputra, et al.
0

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 the transformed dataset.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/04/2019

Exploring Neural Net Augmentation to BERT for Question Answering on SQUAD 2.0

Enhancing machine capabilities to answer questions has been a topic of c...
research
02/08/2022

Integrating question answering and text-to-SQL in Portuguese

Deep learning transformers have drastically improved systems that automa...
research
05/01/2019

Declarative Question Answering over Knowledge Bases containing Natural Language Text with Answer Set Programming

While in recent years machine learning (ML) based approaches have been t...
research
02/05/2020

UNCC Biomedical Semantic Question Answering Systems. BioASQ: Task-7B, Phase-B

In this paper, we detail our submission to the 2019, 7th year, BioASQ co...
research
12/28/2020

Causal Perception in Question-Answering Systems

Root cause analysis is a common data analysis task. While question-answe...
research
03/30/2020

NukeBERT: A Pre-trained language model for Low Resource Nuclear Domain

Significant advances have been made in recent years on Natural Language ...
research
04/26/2022

Science Checker: Extractive-Boolean Question Answering For Scientific Fact Checking

With the explosive growth of scientific publications, making the synthes...

Please sign up or login with your details

Forgot password? Click here to reset