Abstract
Salient reasoning of commonsense knowledge can help search engines better understand users’ search intentions and improve users’ search experience with intelligent product recommendation. Existing reasoning methods only use triple classification to determine the rationality of different entities in the knowledge graph, ignoring the significant changes between entities due to different search scenarios, and thus cannot infer the user’s true search intent. In order to solve the above problems, this paper tries various methods to improve the performance of the salient commonsense reasoning model, and proposes a multi-task learning model based on entity type discrimination and entity commonsense saliency reasoning, and at the same time proposes a Prompt-based commonsense saliency inference model. The model proposed won the first place in both the preliminary and semi-finals in the commodity commonsense knowledge saliency reasoning track of the 2022 China Conference on Knowledge Graph and Semantic Computing.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Liu, Q., et al.: Knowledge graph construction techniques. J. Comput. Res. Dev. 53(3), 582–600 (2016)
Vaswani, A., et al.: Attention is all you need. arXiv:1706.03762 (2017)
Devlin, J., et al.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv: 1810.04805 (2019)
Xiao, D., et al.: ERNIE-Gram: pre-training with explicitly N-Gram masked language modeling for natural language understanding. arXiv: 2010.12148 (2020)
Cui, Y., et al.: Revisiting pre-trained models for Chinese natural language processing. arXiv: 2004.13922 (2020)
Liu, P., et al.: Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing. arXiv:2107.13586 (2021)
Schick, T., Schutze, H.: Exploiting: cloze questions for few shot text classification and natural language inference. arXiv: 2001.07676 (2020)
Yao, L., Mao, C., Luo, Y.: KG-BERT: BERT for knowledge graph completion. arXiv: 1909.03193 (2019)
Xie, X., et al.: From discrimination to generation: knowledge graph completion with generative transformer. arXiv:2202.02113 (2022)
LV, X., et al.: Do pre-trained models benefit knowledge graph completion? a reliable evaluation and a reasonable approach. In: Proceedings of the 60th Conference on Association for Computational Linguistics, pp. 3570–3581 (2022)
Qu, Y.C., et al.: Commonsense knowledge salience evaluation with a benchmark dataset in E-commerce. arXiv:2205.10843 (2022)
Chalier, Y., Razniewski, S., Weikum, G.: Joint reasoning for multi-faceted commonsense knowledge. arXiv:2001.04170 (2020)
Romero, J., et al.: Commonsense properties from query logs and question answering forums. arXiv:1905.10989 (2019)
Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv:1711.05101 (2017)
Lee, D.H.: Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks workshop on challenges in representation learning. ICML 3(2), 896 (2013)
Miyato, T., Dai, A.M., Goodfellow, I.: Adversarial training methods for semi-supervised text classification. arXiv:1605.07725 (2016)
Madry, A., et al.: Towards deep learning models resistant to adversarial attacks. arXiv:1706.06083 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Ma, M., Wu, G., Yang, J. (2022). Research on Salient Reasoning for Commonsense Knowledge. In: Zhang, N., Wang, M., Wu, T., Hu, W., Deng, S. (eds) CCKS 2022 - Evaluation Track. CCKS 2022. Communications in Computer and Information Science, vol 1711. Springer, Singapore. https://doi.org/10.1007/978-981-19-8300-9_22
Download citation
DOI: https://doi.org/10.1007/978-981-19-8300-9_22
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-8299-6
Online ISBN: 978-981-19-8300-9
eBook Packages: Computer ScienceComputer Science (R0)