exacity / exacity/deeplearningbook-chinese

英文长句翻译为中文时,建议多用短句

Open
#189 0 comments 16 reactions 0 assignees View on GitHub
Dominant language
TeX
Stars
37.5k
Forks
9.1k
PR merge metrics
No merged PRs in 30d

Description

英文擅长使用从句,如果直接按句翻译会导致中文没有能力表述长句的意思。读者很难从中文句子中分割出从句的主谓关系,导致理解困难。例如:

20.1 章

> One interesting property of Boltzmann machines when trained with learning rules based on maximum likelihood is that the update for a particular weight connecting two units depends only the statistics of those two units, collected under different distributions: P_{model}(v) and \hat{P}_{data}(v)P_{model} (h | v).

在原文中的翻译是

> 玻尔兹曼机有一个有趣的性质,当基于最大似然的学习规则训练时,连接两个单元的特定权重的更新仅取决于这两个单元在不同分布下收集的统计信息:P_{model}(v) 和 \hat{P}_{data}(v) P_{model}(h | v)。

我觉得如果按下面拆解成短句的方法,阅读效果更好

当我们使用最大似然的学习规则训练玻尔兹曼机时,其有一个有趣的性质。更新连接两个单元权重的方法只依赖着两个权重的统计性质。此统计性质可以从下面两种分布中获得: P_{model}(v) 和 \hat{P}_{data}(v) P_{model}(h | v)。

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.