reorganize sequence 2 sequence. #112
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
lcy-seso
force-pushed
the
refine_seq2seq
branch
5 times, most recently
from
28f9377
to
107d31e
Compare
lcy-seso
force-pushed
the
refine_seq2seq
branch
10 times, most recently
from
96a1cff
to
00eb42a
Compare
kuke
reviewed
Jun 27, 2017
nmt_without_attention/README.md
Outdated
| @@ -84,19 +85,17 @@ encoded_vector = paddle.networks.bidirectional_gru( | |||
|
|
|||
|
|
|||
| ### 无注意力机制的解码器 | |||
| PaddleBook中[机器翻译](https://github.com/PaddlePaddle/book/blob/develop/08.machine_translation/README.cn.md)的相关章节中，已介绍了带注意力机制（Attention Mechanism）的 Encoder-Decoder 结构，本例则介绍的是不带注意力机制的 Encoder-Decoder 结构。关于注意力机制，读者可进一步参考 PaddleBook 和参考文献\[[3](#参考文献)]。 | |||
| -PaddleBook中[机器翻译](https://github.com/PaddlePaddle/book/blob/develop/08.machine_translation/README.cn.md)的相关章节中，已介绍了带注意力机制（Attention Mechanism）的 Encoder-Decoder 结构，本例则介绍的是不带注意力机制的 Encoder-Decoder 结构。关于注意力机制，读者可进一步参考 PaddleBook 和参考文献\[[3](#参考文献)]。 | |||
There was a problem hiding this comment.
"本例则介绍的是" -> "本例介绍的则是"? 感觉会好一点
nmt_without_attention/README.md
Outdated
| * `prob`表示生成句子的得分，随之其后则是翻译生成的句子； | ||
| * `<s>` 表示句子的开始，`<e>`表示一个句子的结束，如果出现了在词典中未包含的词，则用`<unk>`替代。 | ||
| - 第一行为输入的源语言句子。 | ||
| - 第二 ~ `beam_size + 1` 行是柱搜索生成的 `beam_size` 条翻译结果 |
There was a problem hiding this comment.
第二 ~ beam_size + 1 行 -> 第二至第beam_size + 1 行，
在文字中少用符号是不是有好点？anyway，个人偏好。
nmt_without_attention/README.md
Outdated
| - 第一行为输入的源语言句子。 | ||
| - 第二 ~ `beam_size + 1` 行是柱搜索生成的 `beam_size` 条翻译结果 | ||
| - 一行之内以“\t”分隔为两列，第一列是句子的log 概率，第二列是翻译结果的文本。 | ||
| - `<s>` 表示句子的开始，`<e>`表示一个句子的结束，如果出现了在词典中未包含的词，则用`<unk>`替代。 |
There was a problem hiding this comment.
<s> -> 符号<s>， <unk>-> 符号<unk>
| @@ -198,22 +193,25 @@ else: | |||
|
|
|||
There was a problem hiding this comment.
Need to reorganize line 189 because we don't have params --train and --generate now.
nmt_without_attention/README.md
Outdated
| * `<s>` 表示句子的开始，`<e>`表示一个句子的结束，如果出现了在词典中未包含的词，则用`<unk>`替代。 | ||
| - 第一行为输入的源语言句子。 | ||
| - 第二 ~ `beam_size + 1` 行是柱搜索生成的 `beam_size` 条翻译结果 | ||
| - 一行之内以“\t”分隔为两列，第一列是句子的log 概率，第二列是翻译结果的文本。 |
nmt_without_attention/generate.py
Outdated
| def generate(source_dict_dim, target_dict_dim, model_path, beam_size, | ||
| batch_size): | ||
| """ | ||
| sequence generation for NMT |
nmt_without_attention/generate.py
Outdated
|
|
||
| if __name__ == "__main__": | ||
| generate( | ||
| source_dict_dim=3000, |
There was a problem hiding this comment.
source_dict_dim is 30000 in the original configuration. Should 3000 be OK? the same in train.py.
There was a problem hiding this comment.
this is a bug. fix this.
lcy-seso
commented
Jun 28, 2017
nmt_without_attention/README.md
Outdated
| @@ -84,19 +85,17 @@ encoded_vector = paddle.networks.bidirectional_gru( | |||
|
|
|||
|
|
|||
| ### 无注意力机制的解码器 | |||
| PaddleBook中[机器翻译](https://github.com/PaddlePaddle/book/blob/develop/08.machine_translation/README.cn.md)的相关章节中，已介绍了带注意力机制（Attention Mechanism）的 Encoder-Decoder 结构，本例则介绍的是不带注意力机制的 Encoder-Decoder 结构。关于注意力机制，读者可进一步参考 PaddleBook 和参考文献\[[3](#参考文献)]。 | |||
| -PaddleBook中[机器翻译](https://github.com/PaddlePaddle/book/blob/develop/08.machine_translation/README.cn.md)的相关章节中，已介绍了带注意力机制（Attention Mechanism）的 Encoder-Decoder 结构，本例则介绍的是不带注意力机制的 Encoder-Decoder 结构。关于注意力机制，读者可进一步参考 PaddleBook 和参考文献\[[3](#参考文献)]。 | |||
nmt_without_attention/README.md
Outdated
| * `prob`表示生成句子的得分，随之其后则是翻译生成的句子； | ||
| * `<s>` 表示句子的开始，`<e>`表示一个句子的结束，如果出现了在词典中未包含的词，则用`<unk>`替代。 | ||
| - 第一行为输入的源语言句子。 | ||
| - 第二 ~ `beam_size + 1` 行是柱搜索生成的 `beam_size` 条翻译结果 |
nmt_without_attention/README.md
Outdated
| * `<s>` 表示句子的开始，`<e>`表示一个句子的结束，如果出现了在词典中未包含的词，则用`<unk>`替代。 | ||
| - 第一行为输入的源语言句子。 | ||
| - 第二 ~ `beam_size + 1` 行是柱搜索生成的 `beam_size` 条翻译结果 | ||
| - 一行之内以“\t”分隔为两列，第一列是句子的log 概率，第二列是翻译结果的文本。 |
nmt_without_attention/README.md
Outdated
| - 第一行为输入的源语言句子。 | ||
| - 第二 ~ `beam_size + 1` 行是柱搜索生成的 `beam_size` 条翻译结果 | ||
| - 一行之内以“\t”分隔为两列，第一列是句子的log 概率，第二列是翻译结果的文本。 | ||
| - `<s>` 表示句子的开始，`<e>`表示一个句子的结束，如果出现了在词典中未包含的词，则用`<unk>`替代。 |
nmt_without_attention/generate.py
Outdated
|
|
||
| if __name__ == "__main__": | ||
| generate( | ||
| source_dict_dim=3000, |
There was a problem hiding this comment.
this is a bug. fix this.
nmt_without_attention/generate.py
Outdated
| def generate(source_dict_dim, target_dict_dim, model_path, beam_size, | ||
| batch_size): | ||
| """ | ||
| sequence generation for NMT |
| @@ -198,22 +193,25 @@ else: | |||
|
|
|||
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
reorganize codes of attention without attention.