Agriculture Named Entity Recognition—Towards FAIR, Reusable Scholarly Contributions in Agriculture
Round 1
Reviewer 1 Report
Comments and Suggestions for AuthorsIt is noted the lack of information concerning experimental apparatus/ place of study/ or, alternatively, the theoretical approach and related paradigm in which this research emerges.
Consider improving the explanation of research design (observational, experimental, etc. or even of a more qualitative sort), justifying the use of the techniques used to gather, analyze and present the exposed conclusions. It would help some statements regarding the selection of the used sources and sampling methods for the theoretical part of the paper (literature review).
Concerning the Figure 1, the information within the graphs is not readable. Would it be possible to present a bigger version of said Figure, as an appendix?
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 2 Report
Comments and Suggestions for AuthorsIn this paper ,authors are introducing a dataset for NER application in the agriculture domain.
Some acronyms either are not defined, or they are missing.
6 examples instead of 5 in table 2
No mention of the hyperparameters. Please name them.
Although titles can be descriptive of what the authors are trying to tackle, but normally not many of entities are present there. Please elaborate more on this choice.
Please elaborate on the "inexact match" metric more.
Why just use the BERT-Cased model? Why BERT-uncased is not considered, since just the title of the articles are considered?
Since you are using BERT, why BERT tokenizer is not considered for the Char "CNN + Word BiLSTM + CRF" model? A table with these results could be very insightful (for a fair comparison given the sizes of the models)
Comments on the Quality of English LanguageThe language is not easy to follow. It requires extensive language clarity and grammatical improvement.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 3 Report
Comments and Suggestions for AuthorsThis paper introduces the ORKG Agri-NER corpus and service, which focus on extracting and classifying scientific entities in the agricultural domain. The paper describes the creation of the corpus and highlights its features, including a conceptual framework for capturing scientific entities in agriculture, a benchmark for evaluating named entity recognition using neural architectures and transformer models, and an automatic entity resolution procedure using the AGROVOC ontology.
In section 4.1.2, it is suggested that the authors consider incorporating figures to provide visual representations of the neural network and transformer concepts.
In the discussion section, the authors may want to discuss potential future work and directions in this area.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 4 Report
Comments and Suggestions for AuthorsDear Autor,
The text contains many imperfections.
The article is weak and needs thorough additions and descriptions of the interpretation of the results obtained. The article lacks a decent abstract i zawartego w nim celu artykułu, a literature review and a chapter on "Discution" and chapter "Conclutions".
The entire article should undergo a thorough revision from the abstract to the conclusions.
Under the figures, there is a lack of solid interpretations regarding the results obtained in the analysis process.
The article should include an up-to-date review of the scientific literature, because going with the advancement of digital technology, and already Industry 5.0, the literature items should be as up-to-date as possible.
The article is not written according to the jurnal template.
The article as a whole should be rewritten by the authors and thoroughly revised in its entirety.
Author Response
Please see the attachment
Author Response File: Author Response.pdf
Round 2
Reviewer 2 Report
Comments and Suggestions for AuthorsThe modifications look good. Good luck
Comments on the Quality of English LanguageThe English requires a minor revision.
Author Response
We would like to thank the reviewer for their time in reviewing our paper in the second round as well.
-----------------------------------------------------------------------------------------
[R2 comment] Comments on the Quality of English Language
The English requires a minor revision.
[author response]
We will proofread the paper and try at best to address any revisions to the English for the final version.
-------------------------------------------------------------------------------------------
Reviewer 4 Report
Comments and Suggestions for AuthorsThe article still lacks a chapter on conclusions.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf