2000 character limit reached
Extractive and Abstractive Explanations for Fact-Checking and Evaluation of News
Published 27 Apr 2021 in cs.CL | (2104.12918v1)
Abstract: 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 LLM. 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.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.