论文标题
自动编码像素：用图形卷积的摊销变异推断用于功能分布语义
Autoencoding Pixies: Amortised Variational Inference with Graph Convolutions for Functional Distributional Semantics
论文作者
论文摘要
功能分布语义语义通过表示单词作为函数（二进制分类器）而不是向量的含义，为分布语义提供了一个可解释的框架。但是，大量的潜在变量意味着推理在计算上是昂贵的，因此训练模型的收敛缓慢。在本文中，我介绍了Pixie AutoCododer，该编码器通过图形跨斜线神经网络增强了功能分布语义的生成模型，以执行摊销的变分推断。这使该模型可以更有效地训练，从而在两个任务（上下文和语义构图中的语义相似性）上获得更好的结果，并且超过了大型预训练的语言模型BERT。
Functional Distributional Semantics provides a linguistically interpretable framework for distributional semantics, by representing the meaning of a word as a function (a binary classifier), instead of a vector. However, the large number of latent variables means that inference is computationally expensive, and training a model is therefore slow to converge. In this paper, I introduce the Pixie Autoencoder, which augments the generative model of Functional Distributional Semantics with a graph-convolutional neural network to perform amortised variational inference. This allows the model to be trained more effectively, achieving better results on two tasks (semantic similarity in context and semantic composition), and outperforming BERT, a large pre-trained language model.
