学习否定和不确定性的非纠缠表示
Learning Disentangled Representations of Negation and Uncertainty
摘要：
否定和不确定性建模是自然语言处理中长期存在的任务。语言学理论认为，否定和不确定的表达在语义上是相互独立的，也与它们所修饰的内容无关。然而，以前的作品表示学习没有明确的模型这种独立性。因此，我们尝试使用变分自编码器来理清否定、不确定和内容的表示。我们发现，简单地监督潜在的表示结果在良好的解纠缠，但辅助目标的基础上对抗学习和互信息最小化可以提供额外的解纠缠增益。
英文摘要：
Negation and uncertainty modeling are long-standing tasks in natural language processing. Linguistic theory postulates that expressions of negation and uncertainty are semantically independent from each other and the content they modify. However, previous works on representation learning do not explicitly model this independence. We therefore attempt to disentangle the representations of negation, uncertainty, and content using a Variational Autoencoder. We find that simply supervising the latent representations results in good disentanglement, but auxiliary objectives based on adversarial learning and mutual information minimization can provide additional disentanglement gains.
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。
