Hierarchical Bi-Directional Self-Attention Networks for Paper Review Rating Recommendation
Open accessAbstract
Review rating prediction of text reviews is a rapidly growing technology with a wide range of applications in natural language processing.However, most existing methods either use handcrafted features or learn features using deep learning with simple text corpus as input for review rating prediction, ignoring the hierarchies among data.In this paper, we propose a Hierarchical bi-directional self-attention Network framework (HabNet) for paper review rating prediction and recommendation, which can serve as an effective decision-making tool for the academic paper review process.Specifically, we leverage the hierarchical structure of the paper reviews with three levels of encoders: sentence encoder (level one), intra-review encoder (level two) and interreview encoder (level three).Each encoder first derives contextual representation of each level, then generates a higher-level representation, and after the learning process, we are able to identify useful predictors to make the final acceptance decision, as well as to help discover the inconsistency between numerical review ratings and text sentiment conveyed by reviewers.Furthermore, we introduce two new metrics to evaluate models in data imbalance situations.Extensive experiments on a publicly available dataset (PeerRead) and our own collected dataset (OpenReview) demonstrate the superiority of the proposed approach compared with state-of-the-art methods.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 48,293 · see citing works
SciBERT: A Pretrained Language Model for Scientific Text
Beltagy, I., Lo, K., & Cohan, A. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1371 · Cited by 3,218 · see citing works
A Structured Self-attentive Sentence Embedding
Lin, Z., Feng, M., Santos, C. N. D., Yu, M., Xiang, B., Zhou, B., & Bengio, Y. (2017) · arXiv · doi:10.48550/arxiv.1703.03130 · Cited by 1,743 · see citing works
A Dataset of Peer Reviews (PeerRead): Collection, Insights and NLP Applications
Kang, D., Ammar, W., Dalvi, B., Zuylen, M., Kohlmeier, S., Hovy, E., & Schwartz, R. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1149 · Cited by 171 · cited 2× · see citing works
“Kang et al. (2018) collected a dataset of peer reviews from several conferences and predicted paper acceptance decision by using paper draft.”
BackgroundDoes My Rebuttal Matter? Insights from a Major NLP Conference
Gao, Y., Eger, S., Kuznetsov, I., Gurevych, I., & Miyao, Y. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1129 · Cited by 48 · see citing works
Flagged first, then by citations
Research works printed but not linked: 27
- Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural machine translation by jointly learning to align and translate. In Proceedings of the ICLR.
- Yoshua Bengio, Aaron Courville, and Pascal Vincent. 2013. Representation learning: A review and new perspec- tives. TPAMI, 35(8):1798-1828.
- Kyunghyun Cho, Bart van Merriënboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014. Learning phrase representations using rnn encoder-decoder for statistical machine translation. In Proceedings of the EMNLP, pages 1724-1734.
- Alexis Conneau, Holger Schwenk, Loïc Barrault, and Yann Lecun. 2017. Very deep convolutional networks for text classification. In Proceedings of the EACL, pages 1107-1116.
- Wenliang Gao, Naoki Yoshinaga, Nobuhiro Kaji, and Masaru Kitsuregawa. 2013. Modeling user leniency and product popularity for sentiment classification. In Proceedings of the IJCNLP, pages 1107-1111.
- Junaid Hassan and Umar Shoaib. 2020. Multi-class review rating classification using deep recurrent neural net- work. NPL, 51(1):1031-1048.
- Mohammad Hossin and MN Sulaiman. 2015. A review on evaluation metrics for data classification evaluations. IJDKP, 5(2):1.
- Xinyu Hua, Mitko Nikolov, Nikhil Badugu, and Lu Wang. 2019. Argument mining for understanding peer reviews. In Proceedings of the NAACL, pages 2131-2137.
- Rie Johnson and Tong Zhang. 2017. Deep pyramid convolutional neural networks for text categorization. In Proceedings of the ACL, pages 562-570.
- Yoon Kim. 2014. Convolutional neural networks for sentence classification. In Proceedings of the EMNLP, pages 1746-1751.
- Siwei Lai, Liheng Xu, Kang Liu, and Jun Zhao. 2015. Recurrent convolutional neural networks for text classifi- cation. In Proceedings of the AAAI, pages 2267-2273.
- Youfang Leng, Li Yu, and Jie Xiong. 2019. Deepreviewer: Collaborative grammar and innovation neural network for automatic paper review. In Proceedings of the ICMI, pages 395-403.
- Siqing Li, Wayne Xin Zhao, Eddy Jing Yin, and Ji-Rong Wen. 2019. A neural citation count prediction model based on peer review text. In Proceedings of the EMNLP, pages 4916-4926.
- Bo Pang and Lillian Lee. 2005. Seeing stars: Exploiting class relationships for sentiment categorization with respect to rating scales. In Proceedings of the ACL, pages 115-124.
- Hao Peng, Jianxin Li, Yu He, Yaopeng Liu, Mengjiao Bao, Lihong Wang, Yangqiu Song, and Qiang Yang. 2018. Large-scale hierarchical text classification with recursively regularized deep graph-cnn. In Proceedings of the WWW, pages 1063-1072. International World Wide Web Conferences Steering Committee.
- Jeffrey Pennington, Richard Socher, and Christopher Manning. 2014. Glove: Global vectors for word representa- tion. In Proceedings of the EMNLP, pages 1532-1543.
- Chao Qiao, Bo Huang, Guocheng Niu, Daren Li, Daxiang Dong, Wei He, Dianhai Yu, and Hua Wu. 2018. A new method of region embedding for text classification. In Proceedings of the ICLR.
- Lizhen Qu, Georgiana Ifrim, and Gerhard Weikum. 2010. The bag-of-opinions method for review rating prediction from sparse text patterns. In Proceedings of the COLING, pages 913-921. Association for Computational Linguistics.
- Alexander M Rush, Sumit Chopra, and Jason Weston. 2015. A neural attention model for abstractive sentence summarization. In Proceedings of the EMNLP, pages 379-389.
- Tao Shen, Tianyi Zhou, Guodong Long, Jing Jiang, Shirui Pan, and Chengqi Zhang. 2018a. Disan: Directional self-attention network for rnn/cnn-free language understanding. In Proceedings of the AAAI, pages 5446-5455.
- Tao Shen, Tianyi Zhou, Guodong Long, Jing Jiang, and Chengqi Zhang. 2018b. Bi-directional block self-attention for fast and memory-efficient sequence modeling. In Proceedings of the ICLR.
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Proceedings of the NIPS, pages 5998-6008.
- Baoxin Wang. 2018. Disconnected recurrent neural networks for text categorization. In Proceedings of the ACL, pages 2311-2320.
- Zichao Yang, Diyi Yang, Chris Dyer, Xiaodong He, Alex Smola, and Eduard Hovy. 2016. Hierarchical attention networks for document classification. In Proceedings of the NAACL, pages 1480-1489.
- Pengcheng Yang, Xu Sun, Wei Li, and Shuming Ma. 2018. Automatic academic paper rating based on modular- ized hierarchical convolutional neural network. In Proceedings of the ACL, pages 496-502.
- Wenpeng Yin and Hinrich Schütze. 2018. Attentive convolution: Equipping cnns with rnn-style attention mecha- nisms. TACL, 6:687-702.
- DongMei Zhang, Shengen Li, Cuiling Zhu, Xiaofei Niu, and Ling Song. 2010. A comparison study of multi-class sentiment classification for chinese reviews. In Proceedings of the FSK, volume 5, pages 2433-2436. IEEE.
Cited by
Sorted by citations
LLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing
Du, J., Wang, Y., Zhao, W., Deng, Z., Liu, S., Lou, R., Zou, H. P., Narayanan Venkit, P., Zhang, N., Srinath, M., et al. (2024) · Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2024.emnlp-main.292 · Cited by 23 · see citing works
Self-citationMOPRD: A multidisciplinary open peer review dataset
Lin, J., Song, J., Zhou, Z., Chen, Y., & Shi, X. (2022) · arXiv · doi:10.48550/arxiv.2212.04972 · Cited by 11 · see citing works
“Editorial decision prediction is a task of predicting the decision of acceptance, revision, and rejection of a manuscript based on the review comments [5, 11].”
BackgroundLLMs Assist NLP Researchers: Critique Paper (Meta-)Reviewing
Du, J., Wang, Y., Zhao, W., Deng, Z., Liu, S., Lou, R., Zou, H. P., Venkit, P. N., Zhang, N., Srinath, M., et al. (2024) · arXiv · doi:10.48550/arxiv.2406.16253 · Cited by 2 · see citing works
“…the use of AI to assist in automatically generating peer reviews, such as predicting scores (Li et al., 2020; Zhou et al., 2024; Wang et al., 2020; Deng et al., 2020) and writing reviews (Gao et al., 2024; Wang et al., 2020; Yuan et al., 2022; Liu and Shah, 2023) and meta-reviews (Li et al.,…”
MethodSelf-citationChang, Y., Li, Z., Zhang, H., Kong, Y., Wu, Y., So, H. K.-H., Guo, Z., Zhu, L., & Wong, N. (2025) · Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2025.emnlp-main.790 · Cited by 2 · see citing works
- Authors
- Deng, Z., Peng, H., Xia, C., Li, J., He, L., & Yu, P.
- Affiliations
- University of Illinois Chicago (US)
- Beihang University (CN)
- Lehigh University (US)
- Venue
- Proceedings of the 28th International Conference on Computational Linguistics
- Published
- 2020
- Pages
- 6302-6314
- ISSN
- 1525-2477 (ISSN-L)
- OpenAlex
- W3110228087
- Cited by
- 19
- References
- 5
- Citations by year
- 2025: 2 · 2024: 5 · 2023: 6 · 2022: 4 · 2021: 2
- FWCI
- 2.28
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- International Conference on Computational Linguistics (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science Foundation (1909323, 1763325, 1930941)
- National Natural Science Foundation of China (61872022, III-1763325, 62002007, III-1909323, SaTC-1930941)
- Topics
- Physical Sciences › Computer Science › Information Systems › Recommender Systems and Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- self-attention network, hierarchical encoder
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
