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.

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

Update recurrent_group_en.md #9445

Merged
merged 2 commits into from
Apr 3, 2018
Merged

Conversation

zk5580752
Copy link
Contributor

Fix #9013

@CLAassistant
Copy link

CLAassistant commented Mar 28, 2018

CLA assistant check
All committers have signed the CLA.

TBD
## Overview

Sequential data is a major input type dealing with natural language processing tasks.
Copy link
Collaborator

Choose a reason for hiding this comment

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

I think this paragraph can be simpler:

Sequential data is common in natural language processing.

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Sure.


Sequential data is a major input type dealing with natural language processing tasks.

A sentence is a sequence of words. Many sentences form a paragraph further. Therefore, a paragraph can be viewed as a nested sequence with two level, where each element of the sequence is another sequence.
Copy link
Collaborator

Choose a reason for hiding this comment

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

I feel that this paragraph need to "define" the *two-level sequential data", because the next paragraph is going to talk about it.

Sequential data could be recursive. An example of two-level recursive sequential data is that an article is composed of a sequence of sentences, and each sentence a sequence of words.

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Yeah, Chinese document maybe apply this comment as well.


A sentence is a sequence of words. Many sentences form a paragraph further. Therefore, a paragraph can be viewed as a nested sequence with two level, where each element of the sequence is another sequence.

The double-level sequence is a very flexible data organization method supported by PaddlePaddle, which helps us to better describe more complex language data such as discribing paragraphs and several rounds of dialogues. Based on double-level sequence input, we can design and build a flexible, hierarchical RNN model that encodes input data from the word and sentence level, and can also introduce more complex memory mechanisms to better complete some complex language understanding tasks.
Copy link
Collaborator

Choose a reason for hiding this comment

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

I think this paragraph could be shorter and bring the readers' focus to two-level sequences while keeping them informed that we do have the solution to arbitrary level data.

PaddlePaddle and PaddlePaddle v2 support two-level recursive sequential data. For the support of arbitrary levels, please refer to PaddlePaddle Fluid.

Copy link
Contributor Author

Choose a reason for hiding this comment

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

OK, imply PaddlePaddle Fluid for two-level sequence

@wangkuiyi
Copy link
Collaborator

Hello @zk5580752 , Thank you for your positive reply to my comments. I don't see new Git commits after that. Was that because you edited the content but forgot to run git push? Thanks!

Copy link
Contributor Author

@zk5580752 zk5580752 left a comment

Choose a reason for hiding this comment

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

Fix: fix comment on the first three paragraphs

@zk5580752
Copy link
Contributor Author

Sorry, I'm late.

Copy link
Collaborator

@wangkuiyi wangkuiyi left a comment

Choose a reason for hiding this comment

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

Thank you for the contribution! LGTM!

@wangkuiyi wangkuiyi merged commit 3ceff30 into PaddlePaddle:develop Apr 3, 2018
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

4 participants