arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.13838cs.CL
收藏

基于事实的句子自动修改

Automatic Fact-guided Sentence Modification

Massachusetts Institute of Technology(麻省理工学院)

Darsh J Shah, Tal Schuster, Regina Barzilay

摘要:

像维基百科这样的在线百科全书包含大量需要频繁更正和更新的文本。新的信息可能会与现存的《植物志》中的内容相矛盾。在本文中,我们专注于重写这种动态变化的文章。这是一个具有挑战性的约束生成任务,因为输出必须与新信息一致,并适合现有文档的其余部分。为此,我们提出了一个两步的解决方案:(1)我们识别和删除目标文本中的矛盾成分,为给定的索赔,使用一个中立的立场模型;(2)我们扩大剩余的文本,以符合给定的索赔,使用一种新的双编码器序列到序列模型与复制注意。应用于维基百科事实更新数据集,我们的方法成功地为新的索赔生成更新的句子,实现了最高的SARI分数。此外,我们证明,通过这种重写的句子生成合成数据可以成功地增强FEVER事实检查训练数据集,导致相对误差减少13%。

英文摘要:

Online encyclopediae like Wikipedia contain large amounts of text that need frequent corrections and updates. The new information may contradict existing content in encyclopediae. In this paper, we focus on rewriting such dynamically changing articles. This is a challenging constrained generation task, as the output must be consistent with the new information and fit into the rest of the existing document. To this end, we propose a two-step solution: (1) We identify and remove the contradicting components in a target text for a given claim, using a neutralizing stance model; (2) We expand the remaining text to be consistent with the given claim, using a novel two-encoder sequence-to-sequence model with copy attention. Applied to a Wikipedia fact update dataset, our method successfully generates updated sentences for new claims, achieving the highest SARI score. Furthermore, we demonstrate that generating synthetic data through such rewritten sentences can successfully augment the FEVER fact-checking training dataset, leading to a relative error reduction of 13%.

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。

↑