Skip to content
This repository has been archived by the owner on Jan 24, 2024. It is now read-only.

Add chinese translation for Book chapter 8 machine translation #555

Conversation

nickyfantasy
Copy link
Contributor

No description provided.

@daming-lu daming-lu self-requested a review June 22, 2018 23:28
Copy link
Contributor

@jetfuel jetfuel left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I don't see we save the parameter anywhere. How does this network re-use its trained parameters?

Otherwise LGTM.

from functools import partial
import os

dict_size = 30000
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please keep the original comments. They are quite helpful for user to under.

```
```python
def encoder(is_sparse):
# encoder
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

No need for this comment.

- 输入是一个文字序列,被表示成整型的序列。序列中每个元素是文字在字典中的索引。所以,我们定义数据层的数据类型为`integer_value_sequence`(整型序列),序列中每个元素的范围是`[0, source_dict_dim)`。
```python
def train_decoder(context, is_sparse):
# decoder
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

No need for this.

paddle.reader.shuffle(
paddle.dataset.wmt14.train(dict_size), buf_size=1000),
batch_size=batch_size)
```
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can we show some example outputs during training? Should be helpful.

@nickyfantasy nickyfantasy merged commit ac4c123 into PaddlePaddle:high-level-api-branch Jun 22, 2018
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants