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This repository has been archived by the owner on Jan 24, 2024.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

polish chapter 06 #412

Merged
merged 3 commits into from
Sep 16, 2017
Merged

polish chapter 06 #412

merged 3 commits into from
Sep 16, 2017

Conversation

putcn
Copy link
Contributor

@putcn putcn commented Sep 15, 2017

No description provided.

@@ -1,6 +1,6 @@
# Sentiment Analysis

The source codes of this section can be located at [book/understand_sentiment](https://github.com/PaddlePaddle/book/tree/develop/06.understand_sentiment). First-time users may refer to PaddlePaddle for [Installation guide](https://github.com/PaddlePaddle/book/blob/develop/README.md#running-the-book).
The source codes of this section locates at [book/understand_sentiment](https://github.com/PaddlePaddle/book/tree/develop/06.understand_sentiment). First-time users may refer to PaddlePaddle for [Installation guide](https://github.com/PaddlePaddle/book/blob/develop/README.md#running-the-book).
Copy link
Contributor

Choose a reason for hiding this comment

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

It should is located at

@@ -28,15 +28,15 @@ The model we used in this chapter uses **Convolutional Neural Networks** (**CNNs

### Revisit to the Convolutional Neural Networks for Texts (CNN)

The convolutional neural network for texts is introduced in chapter [recommender_system](https://github.com/PaddlePaddle/book/tree/develop/05.recommender_system), here we make a brief overview.
The convolutional neural network for texts is introduced in chapter [recommender_system](https://github.com/PaddlePaddle/book/tree/develop/05.recommender_system), let's have a brief overview.
Copy link
Contributor

Choose a reason for hiding this comment

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

You can change it to here is a brief overview

the paper as following url, but use fewer layrs.
This network uses a bi-directional recurrent network,
consisting three LSTM layers. This configure refers to
the paper with following url, but use fewer layers.
Copy link
Contributor

Choose a reason for hiding this comment

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

Should be consisting of three LSTM layers.

consisting three LSTM layers. This configure is referred to
the paper as following url, but use fewer layrs.
This network uses a bi-directional recurrent network,
consisting three LSTM layers. This configure refers to
Copy link
Contributor

Choose a reason for hiding this comment

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

This configuration is motivated from the following paper, but uses few layers.
Also make the paper a hyperlink and remove the link from the text.

@wangkuiyi wangkuiyi merged commit 4a181bb into PaddlePaddle:develop Sep 16, 2017
@putcn putcn deleted the review_chp06 branch September 16, 2017 20:47
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.

None yet

3 participants