PONE-D-20-35183

A reproducible experimental survey on biomedical sentence similarity

PLOS ONE

Dear Dr. Lara Clares,

Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process.

Please submit your revised manuscript by Jan 23 2021 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.

Please include the following items when submitting your revised manuscript:

• A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'.
• A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'.
• An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'.

If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter.

If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: http://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols

We look forward to receiving your revised manuscript.

Kind regards,

Bridget McInnes, Ph.D.

Academic Editor

PLOS ONE

Journal Requirements:

When submitting your revision, we need you to address these additional requirements.

1. Please ensure that your manuscript meets PLOS ONE's style requirements, including those for file naming. The PLOS ONE style templates can be found at

https://journals.plos.org/plosone/s/file?id=wjVg/PLOSOne_formatting_sample_main_body.pdf and

https://journals.plos.org/plosone/s/file?id=ba62/PLOSOne_formatting_sample_title_authors_affiliations.pdf

2. We note that you have stated that you will provide repository information for your data at acceptance. Should your manuscript be accepted for publication, we will hold it until you provide the relevant accession numbers or DOIs necessary to access your data. If you wish to make changes to your Data Availability statement, please describe these changes in your cover letter and we will update your Data Availability statement to reflect the information you provide.

3.  Thank you for stating the following in the Acknowledgments Section of your manuscript:

"This work has been supported by the UNED predoctoral grant started in April 2019 372

(BICI N7, November 19th, 2018).".

i) We note that you have provided funding information that is not currently declared in your Funding Statement. However, funding information should not appear in the Acknowledgments section or other areas of your manuscript. We will only publish funding information present in the Funding Statement section of the online submission form.

ii) Please remove any funding-related text from the manuscript and let us know how you would like to update your Funding Statement. Currently, your Funding Statement reads as follows:

 

"UNED predoctoral grant started in April 2019 (BICI N7, November 19th, 2018)

https://www.uned.es/

The funders had and will not have a role in study design, data collection and analysis, decision to publish, or preparation of the manuscript."

 iii) Please include your amended statements within your cover letter; we will change the online submission form on your behalf.

[Note: HTML markup is below. Please do not edit.]

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. Does the manuscript provide a valid rationale for the proposed study, with clearly identified and justified research questions?

The research question outlined is expected to address a valid academic problem or topic and contribute to the base of knowledge in the field.

Reviewer #1: Yes

Reviewer #2: Partly

**********

2. Is the protocol technically sound and planned in a manner that will lead to a meaningful outcome and allow testing the stated hypotheses?

The manuscript should describe the methods in sufficient detail to prevent undisclosed flexibility in the experimental procedure or analysis pipeline, including sufficient outcome-neutral conditions (e.g. necessary controls, absence of floor or ceiling effects) to test the proposed hypotheses and a statistical power analysis where applicable. As there may be aspects of the methodology and analysis which can only be refined once the work is undertaken, authors should outline potential assumptions and explicitly describe what aspects of the proposed analyses, if any, are exploratory.

Reviewer #1: Partly

Reviewer #2: Partly

**********

3. Is the methodology feasible and described in sufficient detail to allow the work to be replicable?

Reviewer #1: Yes

Reviewer #2: No

**********

4. Have the authors described where all data underlying the findings will be made available when the study is complete?

The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception, at the time of publication. The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #1: Yes

Reviewer #2: Yes

**********

5. Is the manuscript presented in an intelligible fashion and written in standard English?

PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.

Reviewer #1: Yes

Reviewer #2: No

**********

6. Review Comments to the Author

Please use the space provided to explain your answers to the questions above and, if applicable, provide comments about issues authors must address before this protocol can be accepted for publication. You may also include additional comments for the author, including concerns about research or publication ethics.

You may also provide optional suggestions and comments to authors that they might find helpful in planning their study.

(Please upload your review as an attachment if it exceeds 20,000 characters)

Reviewer #1: This well-written paper describes a project that is of substantial importance to the domain. I have just a few questions and suggestions:

1. What is the difference between RQ1 and RQ2? Please provide more detail in these questions.

2. Please change line 185 from "and named entities, that they have in common or not; and finally. And finally,"

to

"and named entities, that they have in common or not. Finally,"

3. Please add information on how you will handle unexpected barriers while conducting experiments. In the spirit of this requirement from the publisher - "As there may be aspects of the methodology and analysis which can only be refined once the work is undertaken, authors should outline potential assumptions and explicitly describe what aspects of the proposed analyses, if any, are exploratory." - please briefly discuss contingency efforts to handle the unexpected.

4. It would be so useful if you could do a small pilot study, using your system, and report the results.

Reviewer #2: The authors detail in this registered report the design and a project of implementation of a large and reproducible experimental survey on sentence similarity measures for the biomedical domain.

A first concern is related to the research questions, which may result in two or three (RQ1 to RQ5 are similar).

I would suggest the authors to cut this part and to better highlight the motivations instead.

Several sentences are repeated more than twice (e.g. lines 111 to 114, and lines 117 to 120)

The MeSH thesaurus is not an ontology !!

The authors first introduce a categorization of the literature on sentence semantic similarity measures for the general and biomedical language domains, mainly founded on already research. They identify which methods that will be reproduced and evaluated in "planned experiments". How was conducted the choice/selection of those methods ? It is not obvious.

What was the strategy to identify the related publications ? Was it inspired from systematic review or meta-analysis ?

With more than 100 references, the survey is very well documented. I would suggest the authors to have also a look to the following survey on clinical natural processing : "Hahn U, Oleynik M. Medical Information Extraction in the Age of Deep Learning. Yearb Med Inform. 2020 Aug;29(1):208-220. doi: 10.1055/s-0040-1702001. Epub 2020 Aug 21. PMID: 32823318; PMCID: PMC7442512."

The authors detail their experimental setup by describing their evaluation's plan in order to compare most of the sentence similarity methods with seven goals related to the research questions and motivation.

The first step of the pipeline is preprocessing with four stages. Nothing is said here about the choices. Why UMLS ? Why MetaMap and what are the features/options ? why teokenizing ? what is the impact of tokenizing instead of using lexicons ? What is the original aim of preprocessing ?

I would suggest the authors to detail give the ref of M8, M9, M10, M13, M14, ... (line 265) instead of letting the readers to refer to table 2 or table 3...

line 303 MedSTS or MedSTS full ? what is the difference ?

In don't think that the table 7 (planned results...) will be clear enough to help in answering the research questions enumerated in page 3. Moreover, the registered report lacks a section in which the authors would explain how it is intended to answer to the RQ, which step of the pipeline/workflow is concerned to the RQ. It also lacks a gantt with the tasks and the schedule/timeline. Since a large part of the work still needs to be developed, what kind of methodological software development is envisaged ? What are the technological issues/locks to be removed ?

Finally, what would be the general conclusion of the comparison? A set of proposed methods ? To do what ? Since the application domains of sentence similarity, categorizing the methods according to the aim of sentence similarity is another axis to be considered here.

Minor comments :

line 34 desambiguate acronym MeSH

line 37 desambiguate MIMIC

line 39 Pubmed -> PubMed

line 42 desambiguate BERT

line 64 desambiguate HESML

line 85 desambigiate NER

line 105 BIOSSES ?

line 106 MedSTS, CTR ?

line 164 SNOMED-CT ?

line 173 SWEM ?

line 185 "; and finally. And finally," ?

line 192 WBSM? UBSM?

line 212 ELMo ?

line 226 Metamap --> MetaMap

line 233 UMLS ?

line 234 METAMAP --> MetaMap

line 237 char ?

Incomplete references

43. Lastra-D ́ıaz JJ, Goikoetxea J, Hadj Taieb MA, Garc ́ıa-Serrano A, Aouicha MB, Agirre E. A reproducible survey on word embeddings and ontology-based methods for word similarity: linear combinations outperform the state of the art. Engineering Applications of Artificial Intelligence. 2019;.

57 Agirre E, Banea C, Cer D, Diab M, others. Semeval-2016 task 1: Semantic textual similarity, monolingual and cross-lingual evaluation. Workshop on Semantic . . . . 2016;.

58. Cer D, Diab M, Agirre E, Lopez-Gazpio I, Specia L. SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation. arXiv. 2017;.

69. Shen D, Wang G, Wang W, Min MR, Su Q, Zhang Y, et al. Baseline Needs More Love: On Simple Word-Embedding-Based Models and Associated Pooling Mechanisms. arXiv. 2018;.

71. Chen Q, Du J, Kim S, Wilbur WJ, Lu Z. Combining rich features and deep learning for finding similar sentences in electronic medical records. Proc of the BioCreative/OHNLP Challenge. 2018;.

81. Pawar A, Mago V. Calculating the similarity between words and sentences using a lexical database and corpus statistics. arXiv. 2018;.

86. Newman-Griffis D, Lai AM, Fosler-Lussier E. Insights into Analogy Completion from the Biomedical Domain. arXiv. 2017;.

91. Arora S, Liang Y, Ma T. A Simple but Tough-to-Beat Baseline for Sentence Embeddings; 2016.

95. Beltagy I, Lo K, Cohan A. SciBERT: A Pretrained Language Model for Scientific Text. arXiv. 2019;.

96. Gu Y, Tinn R, Cheng H, Lucas M, Usuyama N, Liu X, et al. Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing. arXiv. 2020;.

97. Wada S, Takeda T, Manabe S, Konishi S, Kamohara J, Matsumura Y. A pre-training technique to localize medical BERT and enhance BioBERT. arXiv. 2020;.

100. Al-Natsheh HT, Martinet L, Muhlenbach F, others. Udl at semeval-2017 task 1: Semantic textual similarity estimation of english sentence pairs using regression model over pairwise features. Proc of the 11th semeval conference. 2017;.

116. Cer D, Yang Y, Kong SY, Hua N, Limtiaco N, St John R, et al. Universal Sentence Encoder. arXiv. 2018;.

117. Huang K, Altosaar J, Ranganath R. ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission. arXiv. 2019;.

72. P Jaccard. --> Jaccard P

**********

7. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy.

Reviewer #1: No

Reviewer #2: Yes: Lina F SOUALMIA

[NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.]

While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/. PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email PLOS at figures@plos.org. Please note that Supporting Information files do not need this step.

Protocol for a reproducible experimental survey on biomedical sentence similarity

PONE-D-20-35183R1

Dear Dr. Lara Clares,

We’re pleased to inform you that your manuscript has been judged scientifically suitable for publication and will be formally accepted for publication once it meets all outstanding technical requirements.

Within one week, you’ll receive an e-mail detailing the required amendments. When these have been addressed, you’ll receive a formal acceptance letter and your manuscript will be scheduled for publication.

An invoice for payment will follow shortly after the formal acceptance. To ensure an efficient process, please log into Editorial Manager at http://www.editorialmanager.com/pone/, click the 'Update My Information' link at the top of the page, and double check that your user information is up-to-date. If you have any billing related questions, please contact our Author Billing department directly at authorbilling@plos.org.

If your institution or institutions have a press office, please notify them about your upcoming paper to help maximize its impact. If they’ll be preparing press materials, please inform our press team as soon as possible -- no later than 48 hours after receiving the formal acceptance. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org.

Kind regards,

Bridget McInnes, Ph.D.

Academic Editor

PLOS ONE

Additional Editor Comments (optional):

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. Does the manuscript provide a valid rationale for the proposed study, with clearly identified and justified research questions?

The research question outlined is expected to address a valid academic problem or topic and contribute to the base of knowledge in the field.

Reviewer #1: Yes

Reviewer #2: Yes

**********

2. Is the protocol technically sound and planned in a manner that will lead to a meaningful outcome and allow testing the stated hypotheses?

The manuscript should describe the methods in sufficient detail to prevent undisclosed flexibility in the experimental procedure or analysis pipeline, including sufficient outcome-neutral conditions (e.g. necessary controls, absence of floor or ceiling effects) to test the proposed hypotheses and a statistical power analysis where applicable. As there may be aspects of the methodology and analysis which can only be refined once the work is undertaken, authors should outline potential assumptions and explicitly describe what aspects of the proposed analyses, if any, are exploratory.

Reviewer #1: Yes

Reviewer #2: Yes

**********

3. Is the methodology feasible and described in sufficient detail to allow the work to be replicable?

Reviewer #1: Yes

Reviewer #2: Yes

**********

4. Have the authors described where all data underlying the findings will be made available when the study is complete?

The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception, at the time of publication. The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #1: Yes

Reviewer #2: Yes

**********

5. Is the manuscript presented in an intelligible fashion and written in standard English?

PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.

Reviewer #1: Yes

Reviewer #2: Yes

**********

6. Review Comments to the Author

Please use the space provided to explain your answers to the questions above and, if applicable, provide comments about issues authors must address before this protocol can be accepted for publication. You may also include additional comments for the author, including concerns about research or publication ethics.

You may also provide optional suggestions and comments to authors that they might find helpful in planning their study.

(Please upload your review as an attachment if it exceeds 20,000 characters)

Reviewer #1: Thank you for addressing my concerns.

The manuscript provide a valid rationale for the proposed study, with clearly identified and justified research questions.

The methodology is feasible and described in detail.

The authors have addressed data access issues for the project as a whole.

The manuscript is well-written, with useful graphics.

Reviewer #2: The authors have significantly improved their manuscript. A lot of work have been done and all the comments of the reviewers have been taken into consideration, including re-writing of several sections, in this revised version.

**********

7. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy.

Reviewer #1: No

Reviewer #2: Yes: Lina F. Soualmia