Next Article in Journal
An 18–19.2 GHz Voltage-Controlled Oscillator with a Compact Varactor-Only Capacitor Array
Previous Article in Journal
Dynamic Optimal Power Flow of Active Distribution Network Based on LSOCR and Its Application Scenarios
 
 
Article
Peer-Review Record

A Method of Sustainable Development for Three Chinese Short-Text Datasets Based on BERT-CAM

Electronics 2023, 12(7), 1531; https://doi.org/10.3390/electronics12071531
by Li Pan 1,*, Wei Hong Lim 2 and Yong Gan 1
Reviewer 1:
Reviewer 2:
Electronics 2023, 12(7), 1531; https://doi.org/10.3390/electronics12071531
Submission received: 22 February 2023 / Revised: 21 March 2023 / Accepted: 21 March 2023 / Published: 24 March 2023
(This article belongs to the Section Computer Science & Engineering)

Round 1

Reviewer 1 Report

1.            The corresponding long forms should accompany all the first usages of abbreviations.  At the same location, the words of the long form should be suitably written in Title Case.  Either the style of ‘long form followed by the abbreviation’ (preferably) or the ‘abbreviation followed by the long form’ should be consistently used throughout the manuscript.

2.            All figures and tables should be cited only by their respective numbers and without reference to accompanying/non-accompanying words like ‘above’ and ‘below’.  Ideally, it is recommended that the authors verify the entire manuscript for compliance with this.

3.            Rephrasing is needed for: ‘The rise of AI has greatly promoted the advance of robots.’  It seems that the authors intended to use the word ‘robotics’.

4.            What is the motivation of the authors to use the abbreviations like ‘D-L’, and ‘T-C’ instead of the more commonly used ones like ‘DL’, and ‘TC’ respectively?

5.            It is recommended that instead of putting a lot of multiple citations together, individual papers be discussed, compared, and contrasted with the proposed work.

6.            It is recommended that the table captions use the word ‘Table’ instead of the word ‘Tab.’.

7.            It is recommended that the entire manuscript be formatted consistently, e.g. for bold formatting of some captions for figures

8.            In the captions of the axes of the graphical figures, it seems that the authors intend to use the forms like ‘Recall (%)’ rather than ‘Recall / %’.

9.            Keeping in view the focus of the research work as well as its results, it is recommended that the title of the manuscript contain the word ‘Chinese’ to emphasize that the proposed research work is for the Chinese language and it may not necessarily work equally well with any other language.

 

10.        It is highly recommended that the authors justify the usage of the word ‘sustainable’ in the body of the manuscript.  It just seems to be used in the title, abstract, keywords, and conclusion.

Author Response

Please check the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Content

----------

The goal of this paper is to develop sustainable Short T-C (ST-C) method using Deep Learning (D-L) in big data environment. First, the text is vectorized by introducing BERT pretraining model. Then, Convolutional Attention Mechanism (CAM) model is proposed by using convolutional neural network (CNN) to capture feature interactions on the time dimension, and using multiple convolutional kernels to obtain more comprehensive feature information.  Finally, by optimizing and merging BERT pre-training model and CAM model, a corresponding BERT-CAM classification model for ST-C is proposed. Through simulation experiments, the results show that the algorithm performance is better than the other three comparison algorithms.

 

Major comments

--------------

 

1. The title: "A sustainable method based on BERT-CAM" 

 

The title is not accuracy and clear.  What is the major feature of the method? What makes the proposed better than other method? What is the name of the proposed method?

 

2. Line 9: "Deep Learn-9 ing (D-L) in big data environment"

 

Tab.1 Experimental environment settings 

 

Are you sure Core i5 16G PC can run deep learning environment ?

 

3. Line 15-17: "Finally, by optimizing and merging BERT pre-training model and CAM model, a corresponding BERT-CAM classification model for ST-C is proposed."

 

In section 3, the author list many model such as BERT, CAN, ST-C.

However, where is the process about  optimizing and merging?

 

 

Evaluation

--------------

 

Given the above, I'm in a position to major revision.

Author Response

Please check the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

I am happy to note that the authors have well considered all the suggestions of the previous round of review.

Author Response

The article has been revised as requested

Reviewer 2 Report

1. Title:”A method of sustainable development in China based on BERT-CAM“

"Table 2 Details of Chinese short-text public data set"

What is the meaning of "in China" in the title ? Do you mean "for Chinese short-text public data set"?

2.  Fig. 1 Structure of BERT-CAM network model.

What is the innovation of this article? BERT-CAM? However, the section 3.1 does not show clear description about BERT-CAM. The author did not compare BERT-CAM with other methods, for example, ERNIE、RoBERTa、XLNet,etc.

3. The writing of this article is still confusing.

 

My suggestion is to find a senior author to rewrite the paper carefully.

 

 

 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 3

Reviewer 2 Report

The title should be "A method of sustainable development for three chinese short-text datasets based on BERT-CAM".

Author Response

Thank you for your valuable comments, for your questions have been carefully modified according to your requirements, and in the text with other colors are expressed.

Back to TopTop