Improved methods to aid unsupervised evidence-based fact checking for online health news

False information in the domain of online health related articles is of great concern,which has been witnessed abundantly in the current pandemic situation of Covid-19.Recent advancements in the field of Machine Learning and Natural Language Processingcan be leveraged to aid people in distinguishing false information from the truth in thedomain of online health articles. Whilst there has been substantial progress in this spaceover the years, research in this area has mainly focused on the sphere of political news.Health fake news is markedly different from fake news in the political context as healthinformation should be evaluated against the most recent and reliable medical resourcessuch as scholarly repositories. However, one of the challenges with such an approachis the retrieval of the pertinent resources. In this work, we formulate two techniquesfor the retrieval of the most relevant authoritative and reliable medical content fromscholarly repositories which can be used to assess veracity of an online health article.The first technique is an unsupervised method of generating queries from claims whichare extracted from an online health article. We propose a three-step approach for it andillustrate that our method is able to generate effective queries which can be used forretrieval of information from medical knowledge databases. The second method involvesa filtering approach for extracting the most relevant information for the claims. Weshow how this can be achieved with the help of state of the art transformer models andillustrate it’s effectiveness over other methods.