Prompt-Based Word-Level Information Injection BERT for Chinese Named Entity Recognition
Round 1
Reviewer 1 Report
Section 4 should be given with more discussion.
Captions for Tables from 2 to 8 should be written with specific information.
As can be seen in Table 3, limitations of the proposed methods should be provided.
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Reviewer 2 Report
related work > Related work
Related studies section looks explanatory, the research gap from previous studies is not identified
cite the equations in text
Dataset should be elaborated.
From[46] ?
check the writings between line 219-224
Terminologies used in Tables 4,5,6,7 are not understandable. Tables 4, 5,6,7 show the superiority of PWII-BERT, in all cases this proposed algorithm gives better result, However, I doubt about the experimentation, authors are not analysed the results as why this particular algorithm is yielding better result. Data and experiment validation is required.
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Reviewer 3 Report
the manuscript‘s content is highly similar to LEBERT(https://aclanthology.org/2021.acl-long.454/), please explain the difference between PWII-BERT and LEBERT, and why not compare with it.
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Round 2
Reviewer 1 Report
The authors have addressed the comments.
Author Response
We feel great thanks for your professional review work on our article.
Reviewer 3 Report
Before accept, There are some minor mistakes that need to be corrected.
1. In the manuscript, many inferences about figures, papers and equations are incorrect. For example, on lines 116, 147, and so on.
2. There are a few English grammatical errors. For example, on line 175, "A conditional Random Field" should be revised as "A Conditional Random Field".
Author Response
Please see the attachment.
Author Response File: Author Response.pdf