This repository has been archived by the owner on Jan 24, 2024. It is now read-only.
飞桨2.0实例教程 — 使用BERT实现自动写诗 #968
Open
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
删除了1312-1315行多余代码，训练和评测verbose改为1并重新生成了输出。
删除了原先的位置，增加了预训练词向量文件夹
修改了两处说明（Line9,190），修改了最近修改时间（Line15）
rewrite some discriptions
|
补充了对输入的详细说明；将数据集替换为飞桨官方数据集；补充了自动写诗的说明；对章节进行了划分和标序
|
1、不建议将 import paddlenlp as ppnlp 直接 import paddlenlp 即可 |
update the newest url for paddlenlp; update the new API for paddlenlp.
merge op of load_dataset for test, dev, and train.
TCChenlong
reviewed
Jun 18, 2021
| "### 3.1 预训练BERT模型\n", | ||
| "古诗生成是一个文本生成的过程，在实际中模型无法获知还未生成的内容，也即BERT中的双向关系中只能捕捉到前向关系而不能捕捉到后向关系。这个限制我们可以通过添加注意力掩码（attention mask）来屏蔽掉后向的关系，使模型无法注意到还未生成的内容，从而使BERT仍能完成文本生成任务。\n", | ||
| "\n", | ||
| "进一步地，我们可以将文本生成简化为基于BERT的词分类模型（理解为词性标注），即赋予每个词一个标签，该标签即该词后的下一个词是什么。因此，我们直接调用PaddleNLP的BERT词分类模型即可看，需注意模型分类的类别为词表长度。" |
There was a problem hiding this comment.
即赋予每个词一个标签，该标签即该词后的下一个词是什么。
这一句的描述不是很清晰，建议补充一个例子来说明；
因此，我们直接调用PaddleNLP的BERT词分类模型即可看，
这一句似乎不全吧？
| }, | ||
| "source": [ | ||
| "## 4. 古诗生成\n", | ||
| "以下，我们定义一个类来利用已经训练好的模型完成古诗生成的任务。在生成古诗的过程中，我们将已经生成的内容作为输入，编码后输入模型，得到输入中每个词对应的分类结果。然后选取最后一个词的分类结果作为下一个待预测的词。下一轮中，刚刚预测的词将加入到已生成的内容中，继续进行下一个词的预测。\n", |
There was a problem hiding this comment.
然后选取最后一个词的分类结果作为下一个待预测的词
这句有点歧义，建议改为：
作为下一个待预测的词 -> 作为根据当前内容要预测的词
| " self.sequence_length = input_length\r\n", | ||
| " self.lower_triangle_mask = paddle.tril(paddle.tensor.full((input_length, input_length), 1, 'float32'))\r\n", | ||
| "\r\n", | ||
| " def forward(self, token, token_type, input_mask, input_length=None):\r\n", |
add more descriptions.
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
No description provided.