自动编码小精灵：使用分布语义函数的图形卷积摊销变分推理(cs.CL)---Donuts_choco

函数分布语义通过表示单词的含义作为函数（二进制分类器）而不是矢量，为分布语义提供了一个语言上可解释的框架。但是，大量的潜在变量意味着推理在计算上成本高昂，因此训练模型收敛速度很慢。本文介绍了Pixie自动编码器，它用图形卷积神经网络扩充功能分布语义的生成模型，以执行摊销变分推理。这样可以更有效地训练模型，使其在这两个任务（上下文和语义组合的语义相似性）上取得更好的结果，甚至优于 BERT，这是一个大型预训练的语义模型。

原文标题：Autoencoding Pixies: Amortised Variational Inference with Graph Convolutions for Functional Distributional Semantics

原文：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.

原文作者：Guy Emerson

原文地址：http://arxiv.org/abs/2005.02991