A Design for Safety (DFS) Semantic Framework Development Based on Natural Language Processing (NLP) for Automated Compliance Checking Using BIM: The Case of China
, Jianjun She 1,2,*, Yixuan Huang 1, Lingzhi Li 1,2, Lei Zhang 3 and Jiashu Zhang 4Round 1
Reviewer 1 Report
Manuscript Number: Buildings-1748929-peer-review-v1
Title: A Design for Safety(DFS) semantic framework development based on Natural Language Processing(NLP) for automated compliance checking using BIM: A case of China
General Comments
This is a well written paper wherein a Natural Language Processing (NLP) method is proposed for dealing with safety regulations, and the results of text mining and data from BIM are used to develop an Ontology Web Language (OWL) for Design for Safety (DFS).
Specific Comments
Page 1 Title
Probably, it is better to make every first letter of Title capital as:
A Design for Safety (DFS) Semantic Framework Development Based on Natural Language Processing (NLP) for Automated Compliance Checking Using BIM: A Case of China
Abstract
Design for Safety(DFS)
Please insert space before the abbreviation as
Design for Safety (DFS)
Natural Language Processing(NLP)
Insert blank space as
Natural Language Processing (NLP)
Building Information Modelling(BIM)
Insert space as
Building Information Modelling (BIM)
Introduction
Page 2 line 49
construction standards a-re violated repeatedly
Remove – in are
Page 2 Line 61
Insert a blank space in
Automated Compliance Checking(ACC)
Page 6 Line 263-264
Figure 1. Proposed framework for the development of Design for Safety(DFS) ontology and Automated Compliance Checking(ACC) rules based on Natural Language Processing(NLP)
Inset space at 3 places as
Figure 1. Proposed framework for the development of Design for Safety (DFS) ontology and Automated Compliance Checking (ACC) rules based on Natural Language Processing (NLP)
Page 8 Figure 3
1500m2 change as 1500 m2
1000m2 change as 1000 m2
Page 12 Line 440
A paragraph must have at least 2 sentences. A single sentence paragraph is written for Figure 9. Write 2 or more sentences for the paragraph.
Page 12 Line 447
SWRL(Semantic Web Rule Language)
Insert a blank space
SWRL (Semantic Web Rule Language)
Page 13 Line 373
in figure 10
Make F capital as in Figure 10
Page 13 Line 476
Lots of blank space is given on page 13. Move the text above the Figure 10. Do not leave the blank page.
Page 17 Line 551-552
Again, a single sentence paragraph is written for Figure 14. Write 2 or more sentences for the paragraph.
Page 18 Line 555-556
Again, a single sentence paragraph is written for Figure 15. Write 2 or more sentences for the paragraph.
Page 22 Funding
National Natural Science Foundation of China(Grant number NSFC-71901120), and the Special project of the Ministry of Housing and Urban-Rural Development of The People's Republic of China(grant number ZLAQ(2019)AQ-4)
Insert space at 2 places
National Natural Science Foundation of China (Grant number NSFC-71901120), and the Special project of the Ministry of Housing and Urban-Rural Development of The People's Republic of China (grant number ZLAQ(2019)AQ-4)
Author Response
Response to Reviewer 1 Comments
Dear Editors and Reviewers:
On behalf of all the co-authors, we would like to express our sincere thanks for your favorable consideration of our submission and your efforts in managing its review process. Also, we appreciate the valuable time and hard work of the reviewers, and most importantly, their positive and constructive comments. These comments have been carefully reviewed and addressed in the point-to-point response. The manuscript has greatly benefited from these valuable comments and we believe that it is suitable for your consideration for publication. Please find our point-to-point response to the comments raised by the editors and reviewers as below.
Point 1:
Page 1 Title
Probably, it is better to make every first letter of Title capital as:
A Design for Safety (DFS) Semantic Framework Development Based on Natural Language Processing (NLP) for Automated Compliance Checking Using BIM: A Case of China
Response 1: Thanks for your detailed review. Now on Page 1 Title, we have made every first letter of Title capital as: A Design for Safety (DFS) Semantic Framework Development Based on Natural Language Processing (NLP) for Automated Compliance Checking Using BIM: A Case of China.
Point 2:
Abstract
Design for Safety(DFS)
Please insert space before the abbreviation as
Design for Safety (DFS)
Natural Language Processing(NLP)
Insert blank space as
Natural Language Processing (NLP)
Response 2: Thanks for your recommendation. Now in the abstract, we have inserted space before the abbreviation as: Design for Safety (DFS), Natural Language Processing (NLP) and Building Information Modelling (BIM).
Point 3:
Introduction
Page 2 line 49
construction standards a-re violated repeatedly
Remove – in are
Response 3: Thanks for the important suggestion. We're sorry for making such a sloppy typo mistake. Now on page 2 line 49, the symbol - in are has been removed.
Point 4:
Page 2 Line 61
Insert a blank space in
Automated Compliance Checking(ACC)
Response 4: Thanks for your detailed review. Now on Page 2 Line 61-62, we have inserted space before the abbreviation as: Automated Compliance Checking (ACC).
Point 5:
Page 6 Line 263-264
Figure 1. Proposed framework for the development of Design for Safety(DFS) ontology and Automated Compliance Checking(ACC) rules based on Natural Language Processing(NLP)
Inset space at 3 places as
Figure 1. Proposed framework for the development of Design for Safety (DFS) ontology and Automated Compliance Checking (ACC) rules based on Natural Language Processing (NLP)
Response 5: Thank you for this suggestion. Now on Page 6 Line 265-266, we have inserted space before the abbreviation at 3 places as: Figure 1. Proposed framework for the development of Design for Safety (DFS) ontology and Automated Compliance Checking (ACC) rules based on Natural Language Processing (NLP).
Point 6:
Page 8 Figure 3
1500m2 change as 1500 m2
1000m2 change as 1000 m2
Response 6: Thanks for your valuable comments. Now on Page 6 Figure 3, we have changed each m2 as m2 in the figure.
Point 7:
Page 12 Line 440
A paragraph must have at least 2 sentences. A single sentence paragraph is written for Figure 9. Write 2 or more sentences for the paragraph.
Response 7: Thanks for your detailed review. Now on Page 12 Line 445-448, we have written 2 sentences for Figure 9 in this paragraph. A sentence is added to illustrate the transformation of safety knowledge in natural language into compliance checking rules in the computer-readable structured language.
Point 8:
Page 12 Line 447
SWRL(Semantic Web Rule Language)
Insert a blank space
SWRL (Semantic Web Rule Language)
Response 8: Thanks for the important suggestion. Now on Page 12 Line 454-455, we have inserted space before the abbreviation as: SWRL (Semantic Web Rule Language).
Point 9:
Page 13 Line 373
in figure 10
Make F capital as in Figure 10
Response 9: Thanks for your comments. Now on Page 13 Line 481, we have made F capital as in Figure 10. In addition, we examined other identical situations in the manuscript. We have made F capital as in Figure 6 on Page 9 Line 379 and in Figure 11 on Page 14 Line 504.
Point 10:
Page 13 Line 476
Lots of blank space is given on page 13. Move the text above the Figure 10. Do not leave the blank page.
Response 10: Thanks for your valuable comments. The typography of this manuscript has been revised and there is now no blank space given on page 13.
Point 11:
Page 17 Line 551-552
Again, a single sentence paragraph is written for Figure 14. Write 2 or more sentences for the paragraph.
Response 11: We sincerely appreciate the valuable comments. Now on Page 16 Line 562-565, we have written 2 sentences for Figure 14 in this paragraph. A sentence is added to illustrate the instance of data properties of DFS ontology. In addition, we examined other identical situations in the manuscript. Now on Page 17 Line 549-551, we have written 2 sentences for Figure 13 in this paragraph. A sentence is added to illustrate the instance of object properties of DFS ontology.
Point 12:
Page 18 Line 555-556
Again, a single sentence paragraph is written for Figure 15. Write 2 or more sentences for the paragraph.
Response 12: Thank you for this suggestion. Now on Page 17 Line 568-570, we have written 2 sentences for Figure 15 in this paragraph. A sentence is added to illustrate the arcs and nodes in the figure.
Point 13:
Page 22 Funding
National Natural Science Foundation of China(Grant number NSFC-71901120), and the Special project of the Ministry of Housing and Urban-Rural Development of The People's Republic of China(grant number ZLAQ(2019)AQ-4)
Insert space at 2 places
National Natural Science Foundation of China (Grant number NSFC-71901120), and the Special project of the Ministry of Housing and Urban-Rural Development of The People's Republic of China (grant number ZLAQ(2019)AQ-4)
Response 13: We sincerely appreciate the valuable comments. Now on Page 24 Funding, we have inserted space before the abbreviation as: National Natural Science Foundation of China (Grant number NSFC-71901120), and the Special project of the Ministry of Housing and Urban-Rural Development of The People's Republic of China (grant number ZLAQ(2019)AQ-4).
Author Response File: 
Author Response.docx
Reviewer 2 Report
The manuscript presents a useful discussion to the profession of managing safety in design by applying rules-based automated compliance checking system. However, there are some points that need consideration.
1- The findings and potential benefits of using NLP-based semantic framework, which have been achieved in the case study, need to be reported in the abstract. They are missing in the current version.
2- The paper clearly expresses the case study, but it is recommended that authors add more information about the findings and benefits of using NLP-based semantic framework, for instance, what type of safety hazards could be detected in the design stage of this case study through the application of NLP-based semantic framework, or how did the implementation of DFS-based compliance checking system improve the safety performance in the proposed case study? etc.
It is said in the abstract: “practicability and scientific feasibility of the proposed framework is verified”. However, there is no data verifying the framework in the “Case Study” section.
3- The manuscript needs proof-reading. There are some typo errors within the text. for example, line 49: “a-re violated”.
Author Response
Dear Editors and Reviewers:
On behalf of all the co-authors, we would like to express our sincere thanks for your favorable consideration of our submission and your efforts in managing its review process. Also, we appreciate the valuable time and hard work of the reviewers, and most importantly, their positive and constructive comments. These comments have been carefully reviewed and addressed in the point-to-point response. The manuscript has greatly benefited from these valuable comments and we believe that it is suitable for your consideration for publication. Please find our point-to-point response to the comments raised by the editors and reviewers as below.
Point 1: The findings and potential benefits of using NLP-based semantic framework, which have been achieved in the case study, need to be reported in the abstract. They are missing in the current version.
Response 1: Thank you for your important review, which makes the abstract expression more comprehensive. In the case study, the findings and potential benefits such as excellent data interoperability and interactivity of the proposed NLP-based semantic framework have been achieved. Now in the revised version, they are added to the abstract. In addition, the efficiency and scientific feasibility of the proposed framework have been illustrated with concrete data. Therefore, the revised abstract based on your comments summarizes the article more comprehensively and appropriately.
Point 2: The paper clearly expresses the case study, but it is recommended that authors add more information about the findings and benefits of using NLP-based semantic framework, for instance, what type of safety hazards could be detected in the design stage of this case study through the application of NLP-based semantic framework, or how did the implementation of DFS-based compliance checking system improve the safety performance in the proposed case study? etc.
It is said in the abstract: “practicability and scientific feasibility of the proposed framework is verified”. However, there is no data verifying the framework in the “Case Study” section.
Response 2: We sincerely appreciate the valuable comments. We are to reply to the second point first because practicability and scientific feasibility should be considered as the findings and benefits of using the NLP-based semantic framework, which deserves to be demonstrated in detail. In the original version, there is no data verifying the framework, so 4.5 Framework testing and the result is added to the case study on Page 20 Line 649 in the modified version. On Page 20 Line 650-672, four information sets with 50 items are generated based on the design information of BIM in the case study, based on which the precision, recall and F1-measure of the NLP-based semantic framework for DFS are calculated. On Page 21 Line 673-687, the meaning of the indicators was detailed and an error analysis is conducted to determine the reasons for compliance check deviations in the framework tests. We believe that this addition can well explain the practicability and scientific feasibility of the proposed framework.
The suggestion that authors add more information about the findings and benefits of using NLP-based semantic framework is also of significance. Table 6. A comparison of compliance checking methods in different items is added to illustrate the advantages and findings of the proposed framework on Page 22 Line 692. The comparison results on Page 22 Line 693-708 show that the NLP-based semantic framework combines the advantages of traditional compliance checking methods. In terms of compliance detection types, given the advantages of ontology and SWRL, the proposed framework can cover most of the compliance inspection regulations like manual comparison methods. In terms of detection speed and efficiency, the proposed framework can take advantage of computers to possess high speed and efficiency. In terms of safety performance improvement, given that Semantic Web technology assists computers to understand non-compliance like the human brain processes information, the proposed framework can match appropriate solutions using SWRL syntax and logical connections between ontology concept classes. We believe that this addition based on your comments would make the results presented more clearly.
Point 3: The manuscript needs proof-reading. There are some typo errors within the text. for example, line 49: “a-re violated”.
Response 3: Thanks for your detailed review. We're sorry for making such a sloppy typo mistake. Now on page 2 line 49, the symbol - in are has been removed. In addition, we examined other identical situations in the manuscript. E.g., spaces are inserted before the abbreviations in title, abstract and body text. Errors that some letters were not capitalized in the original version are also fixed. etc.
Author Response File: Author Response.docx
Round 2
Reviewer 2 Report
The authors have made extensive changes in response to the comments, which have substantially improved the paper, including:
1. The findings and potential benefits of using NLP-based semantic framework have been included in the "Abstract" section.
2. The verification of NLP-based semantic framework has been added to the "Case Study" section.
This manuscript is a resubmission of an earlier submission. The following is a list of the peer review reports and author responses from that submission.
