Abstract
Script event prediction (SEP) aims to choose a correct subsequent event from a candidate list, according to a chain of ordered context events. It is easy for human but difficult for machine to perform such event reasoning. The reason is that human have relevant commonsense knowledge. If we supplement this knowledge from external knowledge bases, machine may be able to improve the reasoning ability. To this end, we introduce a novel approach, named MSK-Net, which consists of Question Encoder, Knowledge Searcher, Knowledge Encoder and Result Predictor. As far as we know, this is the first model utilizing multi-source knowledge to solve SEP problem. Specifically, first we use Question Encoder to encode the question, including candidate event to be judged and context events, focusing on intra-event contextualization and inter-event order information modelling. Then, we use Knowledge Searcher to retrieve relevant knowledge from multi-source knowledge bases (such as ASER and ATOMIC). Third, Knowledge Encoder is used to encode the knowledge retrieved in the second step. Last, Result Predictor gives the final prediction. Experiments on the widely-used multiple choice narrative cloze (MCNC) task demonstrate our approach achieves state-of-the-art performance compared to other methods. Also, it is worth noting that MSK-Net without external knowledge is still very competitive.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
https://hkust-knowcomp.github.io/ASER/html/index.html (we use the core version of ASER 1.0).
- 2.
https://homes.cs.washington.edu/~msap/atomic/ (we use the aggregated data v4_atomic_all_agg.csv).
- 3.
There are 15 relations in ASER data and 5 relation types selected in ATOMIC data.
References
Chambers, N., Jurafsky, D.: Unsupervised learning of narrative event chains. In: ACL 2008, pp. 789–797. The Association for Computer Linguistics (2008)
Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT 2019, pp. 4171–4186. Association for Computational Linguistics (2019)
Ding, X., Liao, K., Liu, T., Li, Z., Duan, J.: Event representation learning enhanced with external commonsense knowledge. In: EMNLP-IJCNLP 2019, pp. 4893–4902. Association for Computational Linguistics (2019)
Granroth-Wilding, M., Clark, S.: What happens next? Event prediction using a compositional neural network model. In: AAAI 2016, pp. 2727–2733. AAAI Press (2016)
Jans, B., Bethard, S., Vulic, I., Moens, M.: Skip N-grams and ranking functions for predicting script events. In: EACL 2012, pp. 336–344. The Association for Computer Linguistics (2012)
Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., Soricut, R.: ALBERT: a lite BERT for self-supervised learning of language representations. In: ICLR 2020 (2020)
Lee, I., Goldwasser, D.: FEEL: featured event embedding learning. In: AAAI 2018, pp. 4840–4847. AAAI Press (2018)
Li, Z., Ding, X., Liu, T.: Constructing narrative event evolutionary graph for script event prediction. In: IJCAI 2018, pp. 4201–4207. ijcai.org (2018)
Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. CoRR abs/1907.11692 (2019)
Lv, S., Qian, W., Huang, L., Han, J., Hu, S.: SAM-Net: integrating event-level and chain-level attentions to predict what happens next. In: AAAI 2019, pp. 6802–6809. AAAI Press (2019)
Lv, S., Zhu, F., Hu, S.: Integrating external event knowledge for script learning. In: COLING 2020, pp. 306–315. International Committee on Computational Linguistics (2020)
Pichotta, K., Mooney, R.J.: Statistical script learning with multi-argument events. In: EACL 2014, pp. 220–229. The Association for Computer Linguistics (2014)
Pichotta, K., Mooney, R.J.: Learning statistical scripts with LSTM recurrent neural networks. In: AAAI 2016, pp. 2800–2806. AAAI Press (2016)
Rashkin, H., Sap, M., Allaway, E., Smith, N.A., Choi, Y.: Event2Mind: Commonsense inference on events, intents, and reactions. In: ACL 2018, pp. 463–473. Association for Computational Linguistics (2018)
Sap, M., et al.: ATOMIC: an atlas of machine commonsense for if-then reasoning. In: AAAI 2019, pp. 3027–3035. AAAI Press (2019)
Schank, R.C., Abelson, R.P.: Scripts, plans, goals and understanding: an inquiry into human knowledge structures. Technical report (1977)
Wang, L., et al.: Multi-level connection enhanced representation learning for script event prediction. In: WWW 2021, pp. 3524–3533. ACM/IW3C2 (2021)
Wang, Z., Zhang, Y., Chang, C.: Integrating order information and event relation for script event prediction. In: EMNLP 2017, pp. 57–67. Association for Computational Linguistics (2017)
Zhang, H., Liu, X., Pan, H., Song, Y., Leung, C.W.: ASER: a large-scale eventuality knowledge graph. In: WWW 2020, pp. 201–211. ACM/IW3C2 (2020)
Zhang, L., Zhou, D., He, Y., Yang, Z.: MERL: multimodal event representation learning in heterogeneous embedding spaces. In: AAAI 2021, pp. 14420–14427. AAAI Press (2021)
Acknowledgements
We would like to thank Jingqi Suo for supporting our script learning related research, and the anonymous reviewers for their valuable comments and suggestions that help improving the quality of this paper.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Yang, S., Zha, D., Xue, C. (2023). MSK-Net: Multi-source Knowledge Base Enhanced Networks for Script Event Prediction. In: Tanveer, M., Agarwal, S., Ozawa, S., Ekbal, A., Jatowt, A. (eds) Neural Information Processing. ICONIP 2022. Communications in Computer and Information Science, vol 1794. Springer, Singapore. https://doi.org/10.1007/978-981-99-1648-1_6
Download citation
DOI: https://doi.org/10.1007/978-981-99-1648-1_6
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-1647-4
Online ISBN: 978-981-99-1648-1
eBook Packages: Computer ScienceComputer Science (R0)