Generating Fluent Fact Checking Explanations with Unsupervised Post-Editing

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningfagfællebedømt


Fact-checking systems have become important tools to verify fake and misguiding news. These systems become more trustworthy when human-readable explanations accompany the veracity labels. However, manual collection of these explanations is expensive and time-consuming. Recent work has used extractive summarization to select a sufficient subset of the most important facts from the ruling comments (RCs) of a professional journalist to obtain fact-checking explanations. However, these explanations lack fluency and sentence coherence. In this work, we present an iterative edit-based algorithm that uses only phrase-level edits to perform unsupervised post-editing of disconnected RCs. To regulate our editing algorithm, we use a scoring function with components including fluency and semantic preservation. In addition, we show the applicability of our approach in a completely unsupervised setting. We experiment with two benchmark datasets, namely LIAR-PLUS and PubHealth. We show that our model generates explanations that are fluent, readable, non-redundant, and cover important information for the fact check.

TidsskriftInformation (Switzerland)
Udgave nummer10
Sider (fra-til)1-18
StatusUdgivet - 2022

Bibliografisk note

Funding Information:
Shailza Jolly was supported by the TU Kaiserslautern CS Ph.D. scholarship program, the BMBF project XAINES (Grant 01IW20005), a STSM grant from the COST project Multi3Generation (CA18231), and the NVIDIA AI Lab (NVAIL) program. Pepa Atanasova has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No 801199. Isabelle Augenstein’s research is further partially funded by a DFF Sapere Aude research leader grant.

Publisher Copyright:
© 2022 by the authors.

ID: 324680448