ReAct: A Review Comment Dataset for Actionability (and more)

  title={ReAct: A Review Comment Dataset for Actionability (and more)},
  author={G. Choudhary and Natwar Modani and Nitish Maurya},
. Review comments play an important role in the evolution of documents. For a large document, the number of review comments may become large, making it difficult for the authors to quickly grasp what the comments are about. It is important to identify the nature of the comments to identify which comments require some action on the part of document authors, along with identifying the types of these comments. In this paper, we introduce an annotated review comment dataset ReAct . The review… 

MOPRD: A multidisciplinary open peer review dataset

A modular guided review comment generation method based on MOPRD, a multidisciplinary open peer review dataset that consists of paper metadata, multiple version manuscripts, review comments, meta-reviews, author’s rebuttal letters, and editorial decisions is designed.



A Dataset of Peer Reviews (PeerRead): Collection, Insights and NLP Applications

The first public dataset of scientific peer reviews available for research purposes (PeerRead v1) is presented and it is shown that simple models can predict whether a paper is accepted with up to 21% error reduction compared to the majority baseline.

Modeling Review Comments

This paper proposes two latent variable models to simultaneously model and extract key pieces of information in reader comments about reviews and results enable classification of comments accurately.

An Unsupervised Approach to Sentence Classification

It is demonstrated that specific sentences in the textual responses collected in an employee satisfaction survey and a product review are useful in understanding concrete issues, grievances and actionable suggestions for improvements.

Identifying actionable messages on social media

This paper proposes a supervised learning framework for domain-aware, large-scale actionability classification of social media messages, derives lexicons, performs an in-depth analysis for over 25 text based features, and explores strategies to handle domains that have limited training data.

Understanding Blogs through the Lens of Readers' Comments

A method to associate comments to the specific parts of the blog and a hierarchical way to categorize the comments as Suggestion, Agreement, Disagreement or Question are described.

Detecting Agreement and Disagreement in Political Debates

The experimental results on Canadian Parliamentary debates and the United State 1960 Presidential Campaign datasets have proven the efficiency of the developed methodology and outperforms the baseline methodologies.

An Open Review of OpenReview: A Critical Analysis of the Machine Learning Conference Review Process

This work critically analyze the review process through a comprehensive study of papers submitted to ICLR between 2017 and 2020, and finds evidence for a gender gap, with female authors receiving lower scores, lower acceptance rates, and fewer citations per paper than their male counterparts.

Universal Sentence Encoder

It is found that transfer learning using sentence embeddings tends to outperform word level transfer with surprisingly good performance with minimal amounts of supervised training data for a transfer task.

RoBERTa: A Robustly Optimized BERT Pretraining Approach

It is found that BERT was significantly undertrained, and can match or exceed the performance of every model published after it, and the best model achieves state-of-the-art results on GLUE, RACE and SQuAD.

Question classification using support vector machines

This paper proposes to use a special kernel function called the tree kernel to enable the SVM to take advantage of the syntactic structures of questions, and describes how the tree Kernel can be computed efficiently by dynamic programming.