Multiple evidence combination for fact-checking of health-related information

Research output: Contribution to conferencePaperpeer-review

11 Downloads (Pure)

Abstract

Fact-checking of health-related claims has be- come necessary in this digital age, where any in- formation posted online is easily available to everyone. The most effective way to verify such claims is by using evidences obtained from reliable sources of medical knowledge, such as PubMed. Recent advances in the field of NLP have helped automate such fact-checking tasks. In this work, we propose a domain- specific BERT-based model using a transfer learning approach for the task of predicting the veracity of claim-evidence pairs for the verification of health-related facts. We also improvise on a method to combine multiple evidences retrieved for a single claim, taking into consideration conflicting evidences as well. We also show how our model can be exploited when labelled data is available and how back- translation can be used to augment data when there is data scarcity.

Original languageEnglish
Publication statusPublished - 13 Jul 2023
Event22nd Workshop on Biomedical Natural Language Processing and Shared Tasks 2023 - Toronto, Canada
Duration: 13 Jul 202313 Jul 2023

Conference

Conference22nd Workshop on Biomedical Natural Language Processing and Shared Tasks 2023
Abbreviated titleBioNLP-ST 2023
Country/TerritoryCanada
CityToronto
Period13/07/202313/07/2023

Fingerprint

Dive into the research topics of 'Multiple evidence combination for fact-checking of health-related information'. Together they form a unique fingerprint.

Cite this