BriefGPT.xyz
Apr, 2019
一种多任务方法用于在句子表示中区分语法和语义
A Multi-Task Approach for Disentangling Syntax and Semantics in Sentence Representations
HTML
PDF
Mingda Chen, Qingming Tang, Sam Wiseman, Kevin Gimpel
TL;DR
本文提出一种基于神经网络的生成模型，使用两个潜变量来表征句子的句法和语义，并通过训练多个损失函数来实现更好的语义和句法表征的分离，将其应用于句子相似性任务中，并发现该模型的语义和句法表征性能均最优且最为分离。
Abstract
We propose a
generative model
for a sentence that uses two
latent variables
, with one intended to represent the syntax of the sentence and the other to represent its semantics. We show we can achieve better disen
→