A Novel Named Entity Recognition Algorithm for Hot Strip Rolling Based on BERT-Imseq2seq-CRF Model

Round 1

Reviewer 1 Report

 The experimental results should outline the reasons why the performance of the comparison algorithm is better or worse.

The conclusion of the paper is very generic. No clear conclusion or outcomes why the proposed algorithm should be used over the existing ones.

There are some grammatical mistakes and confusions, so the quality of English should be improved.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

- The topic of the paper is important and has an impact in real world application namely the steel industry. The problem is clearly presented and the paper is well written. Nevertheless, the organization may be improved: the second section of a paper is usually dedicate to related works and the approach is described is the dedicated section, here, you give some related works in section2. NER application status and at the end of this section you describe the general view of your contributions.  You may give the general view of your approach in the beginning of section 3 just before 3.1 and you may highlight the relevant elements of your contributions at the end of the introduction. 

- You may give some details about the dataset for readers who are not familiarized with the Chinese language. for instance at the beginning of section 4. 

 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

The paper has been modified according to the review comments.