BriefGPT.xyz
Feb, 2018
深度生成模型用于联合对齐和词表示
Deep Generative Model for Joint Alignment and Word Representation
HTML
PDF
Miguel Rios, Wilker Aziz, Khalil Sima'an
TL;DR
使用翻译数据作为词表示模型的语义相关学习信号的源，利用翻译中的等价性作为分布式上下文进行联合嵌入和对齐，通过概率归一化的隐变量词汇对齐实现嵌入词，并比较上下文中的词的重叠度。应用于多个语义任务上获得了良好的性能表现。
Abstract
This work exploits
translation data
as a source of semantically relevant learning signal for models of
word representation
. In particular, we exploit equivalence through translation as a form of distributed conte
→