公开(公告)号：US20170039174A1

公开(公告)日：2017-02-09

申请号：US15229743

申请日：2016-08-05

Applicant: Google Inc.

Inventor： Brian Patrick Strope ,  Matthew Steedman Henderson

IPC: G06F17/22 ,  G06F17/28 ,  G06N3/08 ,  G06F17/24

CPC classification number: G06F17/2264 ,  G06F17/24 ,  G06F17/274 ,  G06F17/28 ,  G06F17/30705 ,  G06N3/0454 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for transforming and classifying text based on analysis of training texts from particular authors. One of the methods includes receiving an input text including one or more words and a requested author; generating a vector stream representing the input text based on an encoder language model and including one or more multi-dimensional vectors associated with associated words of the words of the input text and representing a distribution of contexts in which the associated words occurred in a plurality of training texts; and producing an output text representing a particular transformation of the input text based at least in part on a decoder language model, the generated vector stream, and the requested author.

Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于基于来自特定作者的训练文本的分析来转换和分类文本。 其中一种方法包括接收包括一个或多个单词的输入文本和所请求的作者; 基于编码器语言模型生成表示输入文本的向量流，并且包括与输入文本的单词的关联词相关联的一个或多个多维向量，并且表示在多个 训练文本; 以及至少部分地基于解码器语言模型，所生成的向量流和所请求的作者来产生表示输入文本的特定变换的输出文本。