Automatic Academic Paper Rating Based on Modularized Hierarchical Attention Network
Pages 669 - 681
Abstract
Automatic academic paper rating (AAPR) remains a difficult but useful task to automatically predict whether to accept or reject a paper. Having found more task-specific structure features of academic papers, we present a modularized hierarchical attention network (MHAN) to predict paper quality. MHAN uses a three-level hierarchical attention network to shorten the sequence for each level. In the network, the modularized parameter distinguishes the semantics of functional chapters. And a label-smoothing mechanism is used as a loss function to avoid inappropriate labeling. Compared with MHCNN and plain HAN on an AAPR dataset, MHAN achieves a state-of-the-art accuracy of 65.33%. Ablation experiments show that the proposed methods are effective.
References
[1]
Kang, D., et al.: A dataset of peer reviews (PeerRead): collection, insights and NLP applications. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pp. 1647–1661 (2018)
[2]
Yang, P., Sun, X., Li, W., Ma, S.: Automatic academic paper rating based on modularized hierarchical convolutional neural network. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp. 496–502 (2018)
[3]
Qiao Feng, Xu Lizhen, and Han Xiaowei Meng Xiaofeng, Li Ruixuan, Wang Kanliang, Niu Baoning, Wang Xin, and Zhao Gansen Modularized and attention-based recurrent convolutional neural network for automatic academic paper aspect scoring Web Information Systems and Applications 2018 Cham Springer 68-76
[4]
Leng, Y., Yu, L., Xiong, J.: DeepReviewer: collaborative grammar and innovation neural network for automatic paper review. In: 2019 International Conference on Multimodal Interaction, pp. 395–403 (2019)
[5]
Skorikov, M., Momen, S.: Machine learning approach to predicting the acceptance of academic papers. In: 2020 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT). IEEE (2020)
[6]
Vincent-Lamarre P and Larivière V Textual analysis of artificial intelligence manuscripts reveals features associated with peer review outcome Quant. Sci. Stud. 2021 2 2 662-677
[7]
Shen, A., Salehi, B., Baldwin, T., Qi, J.: A joint model for multimodal document quality assessment. In: 2019 ACM/IEEE Joint Conference on Digital Libraries (JCDL), pp. 107–110. IEEE (2019)
[8]
Hochreiter S and Schmidhuber J Long short-term memory Neural Comput. 1997 9 8 1735-1780
[9]
Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation (2014)
[10]
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
[11]
Kenton, J.D.M.W.C., Toutanova, L.K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of NAACL-HLT, pp. 4171–4186 (2019)
[12]
Yang, Z., Yang, D., Dyer, C., He, X., Smola, A., Hovy, E.: Hierarchical attention networks for document classification. In: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 1480–1489 (2016)
[13]
Beltagy, I., Peters, M.E., Cohan, A.: Longformer: the long-document transformer. arXiv preprint arXiv:2004.05150 (2020)
[14]
Zaheer, M., et al.: Big bird: transformers for longer sequences. Adv. Neural Inf. Process. Syst. 33, 17283–17297 (2020)
[15]
Langford J and Guzdial M The arbitrariness of reviews, and advice for school administrators Commun. ACM 2015 58 4 12-13
[16]
Lin, J., Song, J., Zhou, Z., Shi, X.: Automated scholarly paper review: possibility and challenges. arXiv preprint arXiv:2111.07533 (2021)
[17]
Shibayama S, Yin D, and Matsumoto K Measuring novelty in science with word embedding PLoS ONE 2021 16 7
[18]
Daudaravicius, V.: Automated evaluation of scientific writing: AESW shared task proposal. In: Proceedings of the Tenth Workshop on Innovative Use of NLP for Building Educational Applications, pp. 56–63 (2015)
[19]
Springstein, M., Müller-Budack, E., Ewerth, R.: QuTI! quantifying text-image consistency in multimodal documents. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2575–2579 (2021)
[20]
Hou, Y., Jochim, C., Gleize, M., Bonin, F., Ganguly, D.: TDMSci: a specialized corpus for scientific literature entity tagging of tasks datasets and metrics. In: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pp. 707–714 (2021)
[21]
Gupta, Y., et al.: The effect of pretraining on extractive summarization for scientific documents. In: Proceedings of the Second Workshop on Scholarly Document Processing, pp. 73–82 (2021)
[22]
Wang, Q., Zeng, Q., Huang, L., Knight, K., Ji, H., Rajani, N.F.: ReviewRobot: explainable paper review generation based on knowledge synthesis. In: Proceedings of the 13th International Conference on Natural Language Generation, pp. 384–397 (2020)
[23]
Yuan, W., Liu, P., Neubig, G.: Can we automate scientific reviewing? arXiv preprint arXiv:2102.00176 (2021)
[24]
de Buy Wenniger, G.M., van Dongen, T., Aedmaa, E., Kruitbosch, H.T., Valentijn, E.A., Schomaker, L.: Structure-tags improve text classification for scholarly document quality prediction. In: Proceedings of the First Workshop on Scholarly Document Processing, pp. 158–167 (2020)
[25]
Huang, J.B.: Deep paper gestalt. arXiv preprint arXiv:1812.08775 (2018)
[26]
Kim, Y.: Convolutional neural networks for sentence classification. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1746–1751. Association for Computational Linguistics, Doha, Qatar (2014)
Index Terms
- Automatic Academic Paper Rating Based on Modularized Hierarchical Attention Network
Index terms have been assigned to the content through auto-classification.
Recommendations
Attention Based Hierarchical Aggregation Network for 3D Left Atrial Segmentation
Statistical Atlases and Computational Models of the Heart. Atrial Segmentation and LV Quantification ChallengesAbstractAtrial fibrillation (AF) is the most common type of cardiac arrhythmia. The atrial segmentation is essential for the understanding of the human atria structure which is vital to the AF treatment. In this paper, we propose a novel three-dimensional ...
Hierarchical Attention based Neural Network for Explainable Recommendation
ICMR '19: Proceedings of the 2019 on International Conference on Multimedia RetrievalIn recent years, recommendation systems have attracted more and more attention due to the rapid development of e-commerce. Reviews information can offer help in modeling user's preference and item's performance. Some existing methods utilize reviews for ...
Modularized and Attention-Based Recurrent Convolutional Neural Network for Automatic Academic Paper Aspect Scoring
Web Information Systems and ApplicationsAbstractThousands of academic papers are submitted at top venues each year. Manual audits are time-consuming and laborious. And the result may be influenced by human factors. This paper investigates a modularized and attention-based recurrent ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
Sep 2022
877 pages
ISBN:978-3-031-17119-2
DOI:10.1007/978-3-031-17120-8
- Editors:
- Wei Lu,
- Shujian Huang,
- Yu Hong,
- Xiabing Zhou
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2022.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 24 September 2022
Author Tags
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 26 Sep 2024
Other Metrics
Citations
View Options
View options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in