Benchmarking the Generation of Fact Checking Explanations
This work addresses the need to automate fact-checking explanations to combat misinformation, but it is incremental as it builds on existing summarization methods with new datasets and baselines.
The paper tackles the problem of generating textual justifications for fact-checking claims by benchmarking summarization approaches over unstructured knowledge, showing that claim-driven extractive steps improve abstractive summarization performance and that a combined dataset model retains style information efficiently.
Fighting misinformation is a challenging, yet crucial, task. Despite the growing number of experts being involved in manual fact-checking, this activity is time-consuming and cannot keep up with the ever-increasing amount of Fake News produced daily. Hence, automating this process is necessary to help curb misinformation. Thus far, researchers have mainly focused on claim veracity classification. In this paper, instead, we address the generation of justifications (textual explanation of why a claim is classified as either true or false) and benchmark it with novel datasets and advanced baselines. In particular, we focus on summarization approaches over unstructured knowledge (i.e. news articles) and we experiment with several extractive and abstractive strategies. We employed two datasets with different styles and structures, in order to assess the generalizability of our findings. Results show that in justification production summarization benefits from the claim information, and, in particular, that a claim-driven extractive step improves abstractive summarization performances. Finally, we show that although cross-dataset experiments suffer from performance degradation, a unique model trained on a combination of the two datasets is able to retain style information in an efficient manner.