###
计算机系统应用:2020,29(9):136-141
本文二维码信息
码上扫一扫!
基于矩阵变换的文本风格迁移方法
(1.复旦大学 软件学院, 上海 201203;2.复旦大学 上海市智能信息处理重点实验室, 上海 201203)
Text Style Transfer Based on Matrix Transformation
(1.Software School, Fudan University, Shanghai 201203, China;2.Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai 201203, China)
摘要
图/表
参考文献
相似文献
本文已被:浏览 124次   下载 66
投稿时间:2019-10-27    修订日期:2019-11-20
中文摘要: 文本风格迁移一直是自然语言处理(NLP)中的一个研究热点,近年来,随着文本生成方法的发展,越来越多的工作着眼于不成对(non-parallel)文本风格迁移这一任务.这一任务的目标是,利用不包含一一对应句子的两个或多个不同风格的文本集,学习一个迁移模型,实现改变句子的风格的同时保留句子其他的内容.目前针对该任务,已有一些基于生成对抗网络的迁移算法被提出,但是受限于对抗学习本身的训练不稳定,以及对句子的风格和语义的独立性假设本身不合理,这些方法无法高效的学到迁移效果好的模型.在这篇文章中,我们首次从统计学习的角度给出了文本风格的定义—文本集中语义向量的协方差矩阵,在这种新的观点下,文本的风格依赖于所有句子的语义向量.我们随后提出了一种无学习(learning free)迁移方法,我们只需要预训练一个自编码器来得到句子的语义向量,然后对这些向量进行白化和风格化变换,来实现风格迁移.
Abstract:Text style transfer is always a hot spot in Natural Language Processing (NLP). In recent years, as the development of sequence generation methods, many researchers focus on style transfer on non-parallel corpora. Specifically, this task wants to change the style of the sentence while keeping the original content. To achieve this target, many works have been proposed which based on the generative adversarial network. But due to the instability of adversarial training and the limitation of the independence assumption between the style and semantic information, these methods are hard to learn an effective and efficient transfer model. In this study, motivated by statistic learning methods, a definition of the text style is given. The style of the corpus can be captured by the covariance matrix of its sentences’ semantic vectors. From this perspective, the text style is dependent on all the semantic information. We then propose a learning free transfer method where the only thing we need is a pre-trained auto-encoder to produce the semantic vectors. With a pair of matrix transformations, including whitening transformation and stylizing transformation, performing on these vectors, we achieve text style transfer.
文章编号:7433     中图分类号:    文献标志码:
基金项目:
引用文本:
黄若孜,张谧.基于矩阵变换的文本风格迁移方法.计算机系统应用,2020,29(9):136-141
HUANG Ruo-Zi,ZHANG Mi.Text Style Transfer Based on Matrix Transformation.COMPUTER SYSTEMS APPLICATIONS,2020,29(9):136-141

用微信扫一扫

用微信扫一扫