The review process is essential to ensure the
quality of publications. Recently, the in-
crease o... more The review process is essential to ensure the quality of publications. Recently, the in- crease of submissions for top venues in ma- chine learning and NLP has caused a problem of excessive burden on reviewers and has of- ten caused concerns regarding how this may not only overload reviewers, but also may af- fect the quality of the reviews. An automatic system for assisting with the reviewing pro- cess could be a solution for ameliorating the problem. In this paper, we explore automatic review summary generation for scientific pa- pers. We posit that neural language models have the potential to be valuable candidates for this task. In order to test this hypothesis, we release a new dataset of scientific papers and their reviews, collected from papers published in the NeurIPS conference from 2013 to 2020. We evaluate state of the art neural summariza- tion models, present initial results on the fea- sibility of automatic review summary genera- tion, and propose directions for the future.
The review process is essential to ensure the
quality of publications. Recently, the in-
crease o... more The review process is essential to ensure the quality of publications. Recently, the in- crease of submissions for top venues in ma- chine learning and NLP has caused a problem of excessive burden on reviewers and has of- ten caused concerns regarding how this may not only overload reviewers, but also may af- fect the quality of the reviews. An automatic system for assisting with the reviewing pro- cess could be a solution for ameliorating the problem. In this paper, we explore automatic review summary generation for scientific pa- pers. We posit that neural language models have the potential to be valuable candidates for this task. In order to test this hypothesis, we release a new dataset of scientific papers and their reviews, collected from papers published in the NeurIPS conference from 2013 to 2020. We evaluate state of the art neural summariza- tion models, present initial results on the fea- sibility of automatic review summary genera- tion, and propose directions for the future.
Uploads
Papers by Kiran sss
Drafts by Kiran sss
quality of publications. Recently, the in-
crease of submissions for top venues in ma-
chine learning and NLP has caused a problem
of excessive burden on reviewers and has of-
ten caused concerns regarding how this may
not only overload reviewers, but also may af-
fect the quality of the reviews. An automatic
system for assisting with the reviewing pro-
cess could be a solution for ameliorating the
problem. In this paper, we explore automatic
review summary generation for scientific pa-
pers. We posit that neural language models
have the potential to be valuable candidates for
this task. In order to test this hypothesis, we
release a new dataset of scientific papers and
their reviews, collected from papers published
in the NeurIPS conference from 2013 to 2020.
We evaluate state of the art neural summariza-
tion models, present initial results on the fea-
sibility of automatic review summary genera-
tion, and propose directions for the future.
quality of publications. Recently, the in-
crease of submissions for top venues in ma-
chine learning and NLP has caused a problem
of excessive burden on reviewers and has of-
ten caused concerns regarding how this may
not only overload reviewers, but also may af-
fect the quality of the reviews. An automatic
system for assisting with the reviewing pro-
cess could be a solution for ameliorating the
problem. In this paper, we explore automatic
review summary generation for scientific pa-
pers. We posit that neural language models
have the potential to be valuable candidates for
this task. In order to test this hypothesis, we
release a new dataset of scientific papers and
their reviews, collected from papers published
in the NeurIPS conference from 2013 to 2020.
We evaluate state of the art neural summariza-
tion models, present initial results on the fea-
sibility of automatic review summary genera-
tion, and propose directions for the future.