Most fact checking models for automatic fake news detection are based on reasoning: given a claim with associated evidence, the models aim to estimate the claim veracity based on the supporting or refuting content within the evidence.
Our approach consists of 3 steps: (1) we create an initial run with BM25 and RM3; (2) we estimate credibility and misinformation scores for the documents in the initial run; (3) we merge the relevance, credibility and misinformation scores to re-rank documents in the initial run.
The state of the art in learning meaningful semantic representations of words is the Transformer model and its attention mechanisms.
This report describes the participation of two Danish universities, University of Copenhagen and Aalborg University, in the international search engine competition on COVID-19 (the 2020 TREC-COVID Challenge) organised by the U. S. National Institute of Standards and Technology (NIST) and its Text Retrieval Conference (TREC) division.
We contribute the largest publicly available dataset of naturally occurring factual claims for the purpose of automatic claim verification.
In this paper, we operationalize the viewpoint that compositionality is contextual rather than deterministic, i. e., that whether a phrase is compositional or non-compositional depends on its context.