Next Article in Journal
Vibration Energy at Damage-Based Statistical Approach to Detect Multiple Damages in Roller Bearings
Next Article in Special Issue
Identifying Irregular Financial Operations Using Accountant Comments and Natural Language Processing Techniques
Previous Article in Journal
Advances in the Multiphase Vortex-Induced Vibration Detection Method and Its Vital Technology for Sustainable Industrial Production
Previous Article in Special Issue
KGNER: Improving Chinese Named Entity Recognition by BERT Infused with the Knowledge Graph
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Applied Sciences
Volume 12
Issue 17
10.3390/app12178539
Review Report
applsci-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
Article
Peer-Review Record

Research on Chinese Medical Entity Recognition Based on Multi-Neural Network Fusion and Improved Tri-Training Algorithm

Appl. Sci. 2022, 12(17), 8539; https://doi.org/10.3390/app12178539
by Renlong Qi 1, Pengtao Lv 2,*, Qinghui Zhang 2 and Meng Wu 2
Reviewer 1:
Kadir Çavdar
Reviewer 2:
Ngoc Tan Le
Reviewer 3:
Laith T. Khrais
Appl. Sci. 2022, 12(17), 8539; https://doi.org/10.3390/app12178539
Submission received: 8 August 2022 / Revised: 23 August 2022 / Accepted: 23 August 2022 / Published: 26 August 2022
(This article belongs to the Special Issue Natural Language Processing (NLP) and Applications)

Round 1

Reviewer 1 Report

Although this is a manuscript produced from a local study, it can be considered as an approach that may have global implications. I think that more results can be given in the manuscript and more evaluation can be made with them.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

The paper is very interesting in the NER domain, especially in medical text while dealing with low-resourced annotated corpus. The proposed approach is finely explained. The authors could improve more the paper quality.  

Here are some recommendations. 

Line 126: The reference [29] should be placed after [28].

Line 127: Please give any reference for Tri-training algorithm.

Line 137: LI et al. [32] should be Li et al. 

Line 193: What does it mean IDCNN ? BERT does not be explained in the structure. 

Could you please give some examples for BIO annotated data for training for ?

Section 4.1. Please make a table for training data about how many tokens, characters, words, etc.  

Lines 170, and 172: Model3 should be Model 3. Model4 should be Model 4. And so on for lines 284, 286, 294, 302. 

Lines 280, 321: Tab should be Table. 

In the Table 2, should you mean the precision rate (P) instead of the accuracy rate ? This is not coherent with P, R, and F1 in your evaluation. 

Please give some illustrations of prediction from all models. 

Please make a sub-section for error analysis with some error illustrations from all your proposed models. 

Would you open source your code, such as github or at your choice ?

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

Dear sir 

It is an interesting paper, but please do the improvements based on what I mentioned above and I suggest to change the title.

 Good Luck

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Back to TopTop