More to diverse: Generating diversified responses in a task oriented multimodal dialog system

Mauajama Firdaus; Arunav Pratap Shandeelya; Asif Ekbal

doi:10.1371/journal.pone.0241271

Peer Review History

Original SubmissionFebruary 29, 2020
29 Feb 2020 Author Response Attachments Attachment Submitted filename: Response-file-Feb2020.pdf https://doi.org/10.1371/journal.pone.0241271.r001
23 Jun 2020 Decision Letter - Haoran Xie, Editor PONE-D-20-02925 More to Diverse: Generating Diversified Responses in a Task Oriented Multimodal Dialog System PLOS ONE Dear Dr. Ekbal, 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 Aug 07 2020 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, Haoran Xie 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. Thank you for stating the following financial disclosure: 'IMP/2018/002072 (http://www.imprint-2.in/Imprint-II/HomePage)' At this time, please address the following queries: Please clarify the sources of funding (financial or material support) for your study. List the grants or organizations that supported your study, including funding received from your institution. State what role the funders took in the study. If the funders had no role in your study, please state: “The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.” If any authors received a salary from any of your funders, please state which authors and which funders. If you did not receive any funding for this study, please state: “The authors received no specific funding for this work.” Please include your amended statements within your cover letter; we will change the online submission form on your behalf. 3. PLOS requires an ORCID iD for the corresponding author in Editorial Manager on papers submitted after December 6th, 2016. Please ensure that you have an ORCID iD and that it is validated in Editorial Manager. To do this, go to ‘Update my Information’ (in the upper left-hand corner of the main menu), and click on the Fetch/Validate link next to the ORCID field. This will take you to the ORCID site and allow you to create a new iD or authenticate a pre-existing iD in Editorial Manager. Please see the following video for instructions on linking an ORCID iD to your Editorial Manager account: https://www.youtube.com/watch?v=_xcclfuvtxQ [Note: HTML markup is below. Please do not edit.] Reviewers' comments: Reviewer's Responses to Questions Comments to the Author 1. Is the manuscript technically sound, and do the data support the conclusions? The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented. Reviewer #1: No Reviewer #2: Yes ******** 2. Has the statistical analysis been performed appropriately and rigorously? Reviewer #1: No Reviewer #2: Yes ****** 3. Have the authors made all data underlying the findings in their manuscript fully available? The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). 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 ****** 4. 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 ****** 5. Review Comments to the Author Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters) Reviewer #1: This research paper is based on the previously proposed multimodal system. Due to unimodal systems have got some problems in the dull and boring responses as authors indicated in the section 1.1 and 2.1, authors employed BLOCK fusion technique and used stochastic beam search with Gumble k-tricks to generate diversified responses (described in the section 2.2). Authors have described the methods for proposed multimodal system. However, authors have also got a mention in the Editor’s Comment 3 that PLOS ONE requires experiments, statistics, and other analyses must be performed. I could not find any detail and illustration for the discussion of the section 5 Experiments. There is section 5.1 Implementation Details only. It is difficult to identify if this research is good or not. Reviewer #2: In this paper, the authors propose a hierarchical encoder-decoder framework for generating diversified responses in a multimodal dialogue setup. It first uses the parallel co-attention to attend over the textual and visual contextual information simultaneously. Then, it applies the BLOCK fusion technique to improve multimodal representation learning. Finally, a stochastic beam search with Gumble Top K-tricks is applied to achieve diversified responses generation. Strengths: 1) The structure, formulation, and figures are clear and straightforward. 2) The experimental design is sufficient; the ablative studies help in understanding different components in the model and the corresponding performance tradeoffs. 3) Better performance on the MMD dataset is demonstrated. It shows the efficacy of the proposed model. Weaknesses: 1) The definition of the problem is confusing on page 5. U_{p,j}, and I_{p,j’}, what are the meanings of p, j, and j’? Why does history H_p just contain from (U_1, I_1) to （U_{p-1}, I_{p-1}）? What are the roles of the user U_p and image I_p? More important, as shown in Fig. 1, in the dialogue, S1 sometimes answer with both images and text. But in the paper, the authors just generate the text answer. The author should clarify the definition of the multimodal dialog task. 2) The authors have already introduced and discussed many works related to NLG. To my knowledge, the multimodal dialog task is much closer to the image dialog task. The references related to the dialog task are insufficient. [1] Wu et al. Are you talking to me? Reasoned visual dialog generation through adversarial learning. In CVPR, 2018. [2] Guo et al. Dual visual attention network for visual dialog. In IJCAI, 2019. [3] Guo et al. Textual-Visual Reference-aware Attention Network for Visual Dialog. IEEE Transactions on Image Processing, 2020. 3) The novelty is limited. For example, parallel Co-Attention (PCA), including the BLOCK fusion for multimodal interaction, has been widely applied as a common attention framework. It is unclear about the motivation. Are there any more insights about your proposed model? 4) Fonts in Fig.6 are too small. 5) The implementation details of the politeness classifier in Fig.5 should be given in the paper. 6) Compared with [8] and [38], the performance superiority of the proposed method is inapparent. The authors should give more discussion. ****** 6. 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: No [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. https://doi.org/10.1371/journal.pone.0241271.r002
Revision 1
23 Jul 2020 Author Response Detailed response is attached at the end. Attachments Attachment Submitted filename: Answer_file_PLoS.pdf https://doi.org/10.1371/journal.pone.0241271.r003
2 Sep 2020 Decision Letter - Haoran Xie, Editor PONE-D-20-02925R1 More to Diverse: Generating Diversified Responses in a Task Oriented Multimodal Dialog System PLOS ONE Dear Dr. Ekbal, 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 Oct 17 2020 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, Haoran Xie Academic Editor PLOS ONE [Note: HTML markup is below. Please do not edit.] Reviewers' comments: Reviewer's Responses to Questions Comments to the Author 1. If the authors have adequately addressed your comments raised in a previous round of review and you feel that this manuscript is now acceptable for publication, you may indicate that here to bypass the “Comments to the Author” section, enter your conflict of interest statement in the “Confidential to Editor” section, and submit your "Accept" recommendation. Reviewer #1: (No Response) Reviewer #2: All comments have been addressed ******** 2. Is the manuscript technically sound, and do the data support the conclusions? The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented. Reviewer #1: No Reviewer #2: Yes ****** 3. Has the statistical analysis been performed appropriately and rigorously? Reviewer #1: No Reviewer #2: Yes ****** 4. Have the authors made all data underlying the findings in their manuscript fully available? The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). 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. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters) Reviewer #1: Authors have applied the parallel co-attention technique between the textual utterance and the multiple images present to generate significant attributes and the textual response. Although authors have done the research in the multimodal dialogue system with the parallel co-attention technique, it is still necessary to give some experimental details for this article. In the Section 5.1, authors provided a brief explanation for the implementation details. There are still some key points that authors did not present for the implementation details of experiments about the determination of network parameters as follow： (1). The AMSGrad was be used as the model training optimizer, and dropout was be used to avoid over-fitting that refer to Hinton's publication in 2014. Why the probability of 0.4 was be determined for the model training? Please give experimental details with the statistical analysis in the use of Table and Figure. (2). In the same questions to determination of the fixed learning rate of 0.0004 and LSTM layers of 200, Please give experimental details with the statistical analysis in the use of Table and Figure. Reviewer #2: The authors have adequately addressed my comments; the effort that the authors have made is appreciated. I would like to see this work for publication. ****** 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: No [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. https://doi.org/10.1371/journal.pone.0241271.r004
Revision 2
14 Sep 2020 Author Response We appreciate the comments of the reviewers. In Section 6.3 (Analysis of Network Parameters) of the revised manuscript we have added the complete analysis with respect to the dropout, learning rate and LSTM layers for model fine-tuning. We used Perplexity (PPL) as the primary metric to fine-tune the framework for determining the network parameters in case of dropout and learning rate. After fixing these parameters we do the complete evaluation in terms of both automatic and human metrics for all the baselines and proposed framework. We used politeness accuracy (PA) as the primary metric for determining the number of LSTM layers in the politeness classifier. The dropout probability was determined to be 0.4 by considering the range of 0.1 - 0.8. The statistical analysis of the results for the different values of dropout probability for the proposed framework is provided in Table 3 of the revised manuscript. In Figure 4(a) we depict the performance of the proposed framework in case of dropout. It is evident that the proposed framework performs best when the dropout probability is 0.4. Therefore, for all the experiments (all baselines) we fix the dropout probability as stated. For learning rate we determined the value to be 0.0004, in a similar way as [12, 13, 44]. Also, we cross-verified by taking a range of 0.001 to 0.0001 to determine the learning rate in case of our proposed framework. As shown in Table 3 and Figure 6(b), the proposed framework performs best when the learning rate is fixed at 0.0004. This is in line with the existing literature. In the last paragraph of Section 6.3, we provide the analysis for the LSTM layers in the classifier. For the politeness classifier, we had fixed the LSTM layers at 200 by evaluating the performance of the classifier for the responses generated by our proposed framework. We checked the performance of the classifier by using different layers of LSTM as shown in Table 4 of the revised manuscript. From the Figure 6(c), it is evident that by increasing the number of LSTM layers the performance of the classifier improved with the maximum accuracy being 0.84 in case of 200 layers. On increasing the number of layers the performance declined and eventually became constant with accuracy lesser than the best performing classifier at 200 layers. This analysis helped in deciding the number of LSTM layers for the classifier. Attachments Attachment Submitted filename: Answer_file2_PLoS.pdf https://doi.org/10.1371/journal.pone.0241271.r005
13 Oct 2020 Decision Letter - Haoran Xie, Editor More to Diverse: Generating Diversified Responses in a Task Oriented Multimodal Dialog System PONE-D-20-02925R2 Dear Dr. Ekbal, 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, Haoran Xie Academic Editor PLOS ONE Additional Editor Comments (optional): Reviewers' comments: Reviewer's Responses to Questions Comments to the Author 1. If the authors have adequately addressed your comments raised in a previous round of review and you feel that this manuscript is now acceptable for publication, you may indicate that here to bypass the “Comments to the Author” section, enter your conflict of interest statement in the “Confidential to Editor” section, and submit your "Accept" recommendation. Reviewer #1: All comments have been addressed ******** 2. Is the manuscript technically sound, and do the data support the conclusions? The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented. Reviewer #1: Yes ****** 3. Has the statistical analysis been performed appropriately and rigorously? Reviewer #1: Yes ****** 4. Have the authors made all data underlying the findings in their manuscript fully available? The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). 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 ****** 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 ****** 6. Review Comments to the Author Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters) Reviewer #1: (No Response) ****** 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 https://doi.org/10.1371/journal.pone.0241271.r006
Formally Accepted
27 Oct 2020 Acceptance Letter - Haoran Xie, Editor PONE-D-20-02925R2 More to Diverse: Generating Diversified Responses in a Task Oriented Multimodal Dialog System Dear Dr. Ekbal: I'm pleased to inform you that your manuscript has been deemed suitable for publication in PLOS ONE. Congratulations! Your manuscript is now with our production department. If your institution or institutions have a press office, please let them know about your upcoming paper now to help maximize its impact. If they'll be preparing press materials, please inform our press team within the next 48 hours. 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. If we can help with anything else, please email us at plosone@plos.org. Thank you for submitting your work to PLOS ONE and supporting open access. Kind regards, PLOS ONE Editorial Office Staff on behalf of Professor Haoran Xie Academic Editor PLOS ONE https://doi.org/10.1371/journal.pone.0241271.r007

Open letter on the publication of peer review reports

PLOS recognizes the benefits of transparency in the peer review process. Therefore, we enable the publication of all of the content of peer review and author responses alongside final, published articles. Reviewers remain anonymous, unless they choose to reveal their names.

We encourage other journals to join us in this initiative. We hope that our action inspires the community, including researchers, research funders, and research institutions, to recognize the benefits of published peer review reports for all parts of the research system.

Learn more at ASAPbio .