arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.04778cs.CL
收藏

事实增强合成新闻生成

Fact-Enhanced Synthetic News Generation

Worcester Polytechnic Institute(伍斯特理工学院);Arizona State University(亚利桑那州立大学);Illinois Institute of Technology(伊利诺伊理工学院)

Kai Shu, Yichuan Li, Kaize Ding, Huan Liu

摘要:

先进的文本生成方法在文本摘要、语言翻译和综合新闻生成方面取得了巨大的成功。然而,这些技术可能会被滥用,产生虚假信息和假新闻。为了更好地了解合成新闻的潜在威胁,我们开发了新一代方法FactGen来生成高质量的新闻内容。现有的文本生成方法要么提供有限的补充信息,要么失去了输入和输出之间的一致性,这使得合成新闻不太可信。为了解决这些问题,FactGen检索外部事实以丰富输出,并从生成的内容中重建输入声明,以提高输入和输出之间的一致性。在真实世界数据集上的实验结果表明,FactGen生成的新闻内容一致,包含丰富的事实。我们还讨论了可能的防御方法,以识别这些合成新闻片,如果FactGen被用来生成合成新闻。

英文摘要:

The advanced text generation methods have witnessed great success in text summarization, language translation, and synthetic news generation. However, these techniques can be abused to generate disinformation and fake news. To better understand the potential threats of synthetic news, we develop a new generation method FactGen to generate high-quality news content. The existing text generation methods either afford limited supplementary information or lose consistency between the input and output which makes the synthetic news less trustworthy. To address these issues, FactGen retrieves external facts to enrich the output and reconstructs the input claim from the generated content to improve the consistency among the input and the output. Experiment results on real-world datasets show that the generated news contents of FactGen are consistent and contain rich facts. We also discuss the possible defending method to identify these synthetic news pieces if FactGen is used to generate synthetic news.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑