论文标题
apo-vae：双曲线空间中的文本生成
APo-VAE: Text Generation in Hyperbolic Space
论文作者
论文摘要
自然语言通常表现出固有的层次结构，这些结构以复杂的语法和语义为基础。但是，大多数最先进的深层生成模型仅在欧几里得向量空间中学习嵌入，而无需考虑这种语言的结构属性。在本文中，我们研究了双曲线潜在空间中的文本生成，以学习连续的层次表示。提出了对抗性的繁殖变量自动编码器（apo-vae），其中潜在变量的先前和变异后验通过包裹的正常分布在庞加雷球上定义。通过采用KL Divergence的原始偶对偶的表述，引入了对抗性学习程序，以增强强大的模型训练。语言建模和对话响应生成任务的广泛实验证明了拟议的APO-VAE模型对欧几里得潜在空间中VAE的胜利有效性，这要归功于其在双曲空间中捕获潜在语言层次结构的出色能力。
Natural language often exhibits inherent hierarchical structure ingrained with complex syntax and semantics. However, most state-of-the-art deep generative models learn embeddings only in Euclidean vector space, without accounting for this structural property of language. In this paper, we investigate text generation in a hyperbolic latent space to learn continuous hierarchical representations. An Adversarial Poincare Variational Autoencoder (APo-VAE) is presented, where both the prior and variational posterior of latent variables are defined over a Poincare ball via wrapped normal distributions. By adopting the primal-dual formulation of KL divergence, an adversarial learning procedure is introduced to empower robust model training. Extensive experiments in language modeling and dialog-response generation tasks demonstrate the winning effectiveness of the proposed APo-VAE model over VAEs in Euclidean latent space, thanks to its superb capabilities in capturing latent language hierarchies in hyperbolic space.
