Embedding Dense Event Graph for Script Event Prediction

被引：0
|
作者：
Ning Z. [1 ]
Jia M. [2 ]
An Y. [3 ]
Duan J. [2 ]
机构：
[1] Key Laboratory of Network Crime Investigation, Hunan Provincial Colleges, Hunan Police Academy, Changsha
[2] School of Computer Science and Engineering, Central South University, Changsha
[3] Big Data Institute, Central South University, Changsha
来源：
Hunan Daxue Xuebao/Journal of Hunan University Natural Sciences | 2023年 / 50卷 / 08期
关键词：
dense event graph; event extraction; graph convolutional networks; script event prediction;
D O I：
10.16339/j.cnki.hdxbzkb.2023293
中图分类号：
学科分类号：
摘要：
Script Event Prediction refers to predicting the subsequent event based on a given existing chain of context events. In the real world，the relationship of different events can be naturally represented as a graph structure，where events serve as nodes and their temporal or causal relations are depicted as edges. However，previous approaches that automatically constructed event graphs suffer from sparsity problem due to the limited scale of corpus and the incapability of information extraction tools. Moreover，they fail to integrate information from higher order nodes to support multi-step reasoning. To remedy this，we propose a Dense Event Graph（DEG）approach which use a learnable multi-dimensional weighted adjacency matrix to address the sparsity issue and characterize the relation strengths between events. To embed the DEG，we propose a general framework capable of combining high-order event evolution information into the event representations. Experimental results on the multiple choice narrative cloze（MCNC）and coherent multiple choice narrative cloze（CMCNC）demonstrate the effectiveness of our approach. © 2023 Hunan University. All rights reserved.
引用
收藏
页码：213 / 222
页数：9
相关论文
共 26 条
  • [1] CHAMBERS N, JURAFSKY D．, Unsupervised Learning of Narrative Event Chains［C］, ACL 2008 Meeting of the Association for Computational Linguistics, (2008)
  • [2] GRANROTH-WILDING M，, CLARK S．, What happens next？event prediction using a compositional neural network model［C］, Proceedings of the AAAI Conference on Artificial Intelligence, pp. 2727-2733, (2016)
  • [3] Skip n-grams and ranking functions for predicting script events［C］, Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics, pp. 336-344, (2012)
  • [4] DING X A, ZHANG Y E，, LIU T, Using structured events to predict stock price movement：an empirical investigation［C］, Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing（EMNLP）Doha，Qatar, pp. 1415-1425, (2014)
  • [5] DING X, ZHANG Y, Et al., Knowledge-driven event embedding for stock prediction［C］, COLING 2016, pp. 2133-2142, (2016)
  • [6] WEBER N, CHAMBERS N．, Event representations with tensor-based compositions［C］, Proceedings of the AAAI Conference on Artificial Intelligence, (2018)
  • [7] MOONEY R．, Learning statistical scripts with LSTM recurrent neural networks［C］, Proceedings of the AAAI Conference on Artificial Intelligence, pp. 2800-2806, (2016)
  • [8] WANG Z Q, ZHANG Y E, CHANG C Y．, Integrating order information and event relation for script event prediction［C］, Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 57-67, (2017)
  • [9] SCARSELLI F．, A new model for learning in graph domains ［C］, Proceedings of 2005 IEEE International Joint Conference on Neural Networks, pp. 729-734, (2005)
  • [10] The graph neural network model［J］．, IEEE Transactions on Neural Networks, 20, 1, pp. 61-80, (2009)
123