Extractive and Abstractive Explanations for Fact-Checking and Evaluation of News
This work addresses the challenge of automating explanation generation for fact-checking, which could aid journalists and platforms in evaluating news credibility, though it appears incremental as it compares existing methods on new data.
The paper tackled the problem of generating natural language explanations for news claims to assist fact-checking and news evaluation, finding that an extractive method based on Biased TextRank showed the most promise in evaluations on political and health misinformation datasets.
In this paper, we explore the construction of natural language explanations for news claims, with the goal of assisting fact-checking and news evaluation applications. We experiment with two methods: (1) an extractive method based on Biased TextRank -- a resource-effective unsupervised graph-based algorithm for content extraction; and (2) an abstractive method based on the GPT-2 language model. We perform comparative evaluations on two misinformation datasets in the political and health news domains, and find that the extractive method shows the most promise.