Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

fix an error in word2vec.md #1318

Open
wants to merge 2 commits into
base: master
Choose a base branch
from
Open

fix an error in word2vec.md #1318

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9d2e087
fix an error in word2vec.md
tscxk Jan 23, 2024
f7a463d
fix an error in word2vec.md
tscxk Feb 22, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions chapter_natural-language-processing-pretraining/word2vec.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@ $$\frac{\mathbf{x}^\top \mathbf{y}}{\|\mathbf{x}\| \|\mathbf{y}\|} \in [-1, 1].$
## 跳元模型（Skip-Gram）
:label:`subsec_skip-gram`

跳元模型假设一个词可以用来在文本序列中生成其周围的单词。以文本序列“the”“man”“loves”“his”“son”为例。假设*中心词*选择“loves”，并将上下文窗口设置为2，如图 :numref:`fig_skip_gram`所示，给定中心词“loves”，跳元模型考虑生成*上下文词*“the”“man”“him”“son”的条件概率：
跳元模型假设一个词可以用来在文本序列中生成其周围的单词。以文本序列“the”“man”“loves”“his”“son”为例。假设*中心词*选择“loves”，并将上下文窗口设置为2，如图 :numref:`fig_skip_gram`所示，给定中心词“loves”，跳元模型考虑生成*上下文词*“the”“man”“his”“son”的条件概率：

$$P(\textrm{"the"},\textrm{"man"},\textrm{"his"},\textrm{"son"}\mid\textrm{"loves"}).$$

Expand Down Expand Up @@ -71,7 +71,7 @@ $$\begin{aligned}\frac{\partial \text{log}\, P(w_o \mid w_c)}{\partial \mathbf{v

## 连续词袋（CBOW）模型

*连续词袋*（CBOW）模型类似于跳元模型。与跳元模型的主要区别在于，连续词袋模型假设中心词是基于其在文本序列中的周围上下文词生成的。例如，在文本序列“the”“man”“loves”“his”“son”中，在“loves”为中心词且上下文窗口为2的情况下，连续词袋模型考虑基于上下文词“the”“man”“him”“son”（如 :numref:`fig_cbow`所示）生成中心词“loves”的条件概率，即：
*连续词袋*（CBOW）模型类似于跳元模型。与跳元模型的主要区别在于，连续词袋模型假设中心词是基于其在文本序列中的周围上下文词生成的。例如，在文本序列“the”“man”“loves”“his”“son”中，在“loves”为中心词且上下文窗口为2的情况下，连续词袋模型考虑基于上下文词“the”“man”“his”“son”（如 :numref:`fig_cbow`所示）生成中心词“loves”的条件概率，即：

$$P(\textrm{"loves"}\mid\textrm{"the"},\textrm{"man"},\textrm{"his"},\textrm{"son"}).$$

Expand Down
Loading