AT-CRF: A Chinese Reading Comprehension Algorithm Based on Attention Mechanism and Conditional Random Fields

Round 1

Reviewer 1 Report

The paper is very well written and the authors have investigated a very timely and important topic in the manuscript. I have the following minor comments;

What is the confidence interval of the results presented in the paper?

The general trend of the results in Fig. 5 shows that F1 Score and EM increase with the increase in the passage length. However, at some points in the graph, it does not support the claim. For example, for a passage length of 250 EM and F1 scores are less than the passage length of 200. Authors need to perform more simulation rounds and present average results.

Authors are suggested to thoroughly revise the manuscript to rectify some very minor grammatical mistakes and typos.

Author Response

Dear reviewer:

We thank you for the time and effort that you have put into reviewing the previous version of the manuscript. Your suggestions have enabled us to improve our work. Based on the instructions provided in your review report, we uploaded the file of the revised manuscript and our point-by-point response to the comments, please see the attachment.

Yours Sincerely,

Nawei Shi

Author Response File: Author Response.pdf

Reviewer 2 Report

The work presents a very relevant and current theme. Thus, I highlight the following points:

1) In the introduction, it is not clear what the gap presented in state of the art, and also how this work will act to fill this gap;

2) There is a need to verify the spacing of the inserted citation;

3) The inserted results do not show the contributions of the development carried out;

4) It is necessary to better develop the conclusions of the work because, as it stands, it is very summarized.

Author Response

Dear reviewer:

We thank you for the time and effort that you have put into reviewing the previous version of the manuscript. Your suggestions have enabled us to improve our work. Based on the instructions provided in your review report, we uploaded the file of the revised manuscript and our point-by-point response to the comments, please see the attachment.

Yours Sincerely,

Nawei Shi

Author Response File: Author Response.pdf

Reviewer 3 Report

This paper is based on the Chinese reading comprehension algorithm and the two dataset is used for employing this method. Below are my comments for improving the manuscript.

1)      More up-to-date references must be presented in the reference list. With respect to this new reference list, the introduction section must be revised.

2)      One comparison table must be added for proving the novelty of work.

3)      The authors must provide suitable descriptions regarding the used parameters in Fig. 3 such as c1, … u1, … etc.

4)      The authors must describe well that when for example the Epoch number is 2 what will happen to the accuracy of network? In summary, the authors must explain and draw figures to demonstrate the influence of training parameters in Table 3 for the accuracy of network.

Author Response

Dear reviewer:

We thank you for the time and effort that you have put into reviewing the previous version of the manuscript. Your suggestions have enabled us to improve our work. Based on the instructions provided in your review report, we uploaded the file of the revised manuscript and our point-by-point response to the comments, please see the attachment.

Yours Sincerely,

Nawei Shi

Author Response File: Author Response.pdf

Reviewer 4 Report

Paper is well written

Proposed frame work is good

Result section is good.

Overall is good Paper

Author Response

Dear reviewer:

We thank you for the time and effort that you have put into reviewing the previous version of the manuscript. Your suggestions have enabled us to improve our work. Based on the instructions provided in your review report, we uploaded the file of the revised manuscript and our point-by-point response to the comments, please see the attachment.

Yours Sincerely,

Nawei Shi

Author Response File: Author Response.pdf

Round 2

Reviewer 3 Report

the authors have provided the comments and I have no further comment.