论文标题
通过VAE和某种建筑选择删除语言中语义的语义
Disentangling semantics in language through VAEs and a certain architectural choice
论文作者
论文摘要
我们提出了一种无监督的方法，以获取单一列出语义内容的句子的分离表示。使用修改后的变压器作为构建块，我们训练一个变分的自动编码器将句子转换为固定数量的层次结构结构化的潜在变量。我们研究每个潜在变量在生成中的影响对句子的依赖性结构以及通过开放信息提取模型时产生的谓词结构的影响。我们的模型可以将动词，主题，直接对象和介词对象分为我们确定的潜在变量。我们表明，改变相应的潜在变量会导致在句子中改变这些元素，并且将它们交换在句子夫妇之间会导致预期的部分语义互换。
We present an unsupervised method to obtain disentangled representations of sentences that single out semantic content. Using modified Transformers as building blocks, we train a Variational Autoencoder to translate the sentence to a fixed number of hierarchically structured latent variables. We study the influence of each latent variable in generation on the dependency structure of sentences, and on the predicate structure it yields when passed through an Open Information Extraction model. Our model could separate verbs, subjects, direct objects, and prepositional objects into latent variables we identified. We show that varying the corresponding latent variables results in varying these elements in sentences, and that swapping them between couples of sentences leads to the expected partial semantic swap.
