基于SoftLexicon和注意力机制的中文因果关系抽取

崔仕林,闫蓉

PDF(2672 KB)
PDF(2672 KB)
中文信息学报 ›› 2023, Vol. 37 ›› Issue (4) : 81-89.
信息抽取与文本挖掘

基于SoftLexicon和注意力机制的中文因果关系抽取

  • 崔仕林1,2,3,闫蓉1,2,3
作者信息 +

Chinese Causality Extraction Based on SoftLexicon and Attention Mechanism

  • CUI Shilin1,2,3, YAN Rong1,2,3
Author information +
History +

摘要

针对现有中文因果关系抽取方法对因果事件边界难以识别和文本特征表示不充分的问题,该文提出了一种基于外部词汇信息和注意力机制的中文因果关系抽取模型BiLSTM-TWAM+CRF。该模型使用SoftLexicon方法引入外部词汇信息构建词集,解决了因果事件边界难以识别的问题。通过构建的双路关注模块TWAM(Two Way Attention Module),实现了从局部和全局两个角度充分刻画文本特征。实验结果表明,与当前中文因果关系抽取模型相比较,该文所提方法表现出更优的抽取效果。

Abstract

Existing Chinese causality extraction methods is challenged by the issue of causal event boundaries identification and inadequate text features representation. This paper proposes a Chinese causality extraction model BiLSTM-TWAM+CRF which ustilizes external lexical information and attention mechanism. We introduce the external lexical information by using the SoftLexicon to construct word set for determining causal event boundaries. We constructe a Two Way Attention Module (TWAM) to represent text features from both the local and global views. Experimental results show that our proposed method has better performance than the existing Chinese causality extraction methods.

关键词

因果关系抽取 / 序列标注 / 注意力机制

Key words

causal relation extraction / sequence labeling / attention mechanism

引用本文

导出引用
崔仕林,闫蓉. 基于SoftLexicon和注意力机制的中文因果关系抽取. 中文信息学报. 2023, 37(4): 81-89
CUI Shilin, YAN Rong. Chinese Causality Extraction Based on SoftLexicon and Attention Mechanism. Journal of Chinese Information Processing. 2023, 37(4): 81-89

参考文献

[1] 杨竣辉,刘宗田,刘炜,等.基于语义事件因果关系识别[J]. 小型微型计算机系统,2016,37(3): 433-437.
[2] 冯冲,康丽琪,石戈,等.融合对抗学习的因果关系抽取[J]. 自动化学报,2018,44(5): 811-818.
[3] RADINSKY K,DAVIDOVICH S,MARKOVITCH S. Learning causality for news events prediction [C]//Proceedings of the 21st International Conference on World Wide Web, 2012: 909-918.
[4] HASHIMOTO C,TORISAWA K,KLOETZER J,et al. Toward future scenario generation: Extracting event causality exploiting semantic relation,context, and association Features[C]//Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, 2014: 987-997.
[5] GIRJU R. Automatic detection of causal relations for question answering[C]//Proceedings of ACL Workshop on Multilingual Summarization and Question Answering, 2003: 76-83.
[6] ZHANG Y,YANG J. Chinese NER using lattice LSTM [C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, 2018: 1554-1564.
[7] VASWANI A,SHAZEER N,PARMAR N,et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems,2017: 6000-6010.
[8] MA R,PENG M,ZHANG Q,et al. Simplify the usage of lexicon in Chinese NER[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020: 5951-5960.
[9] HU J,SHEN L,SUN G. Squeeze-and-excitation networks [C]//Proceedings of IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018: 7132-7141.
[10] GARCIA D. COATIS: An NLP system to locate expressions of actions connected by causality links[C]//Proceedings of International Conference on Knowledge Engineering and Knowledge Management, 1997: 347-352.
[11] ITTOO A,BOUMA G. Extracting explicit and implicit causal relations from sparse,domain-specific texts[C]//Proceedings of International Conference on Application of Natural Language to Information Systems, 2011: 52-63.
[12] ZHAO S,LIU T,ZHAO S,et al. Event causality extraction based on connectives analysis[J]. Neurocomputing,2016,173: 1943-1950.
[13] NAUTA M,BUCUR D,SEIFERT C. Causal discovery with attention-based convolutional neural networks[J]. Machine Learning and Knowledge Extraction,2019,1(1): 312-340.
[14] ZHANG S,ZHENG D,HU X,et al. Bidirectional long short-term memory networks for relation classification [C]//Proceedings of the 29th Pacific Asia Conference on Language,Information and Computation, 2015: 73-78.
[15] JIN X,WANG X,LUO X,et al. Inter-sentence and implicit causality extraction from Chinese corpus[C]//Proceedings of Pacific-Asia Conference on Knowledge Discovery and Data Mining, 2020: 739-751.
[16] ZENG D,LIU K,LAI S,et al. Relation classification via convolutional deep neural network[C]//Proceedings of the 25th International Conference On Computational Linguistics, 2014: 2335-2344.
[17] ZENG Y,YANG H,FENG Y,et al. A convolution BiLSTM neural network model for Chinese event extraction [C]//Proceedings of Natural Language Understanding and Intelligent Applications,2016: 275-287.
[18] DEVLIN J,CHANG M W,LEE K,et al. BERT: Pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of the North American Chapter of the Association for Computational Linguistics, 2019: 4171-4186.
[19] GAO J,LUO X,WANG H,et al. Causal event extraction using iterated dilated convolutions with semantic convolutional filters[C]//Proceedings of IEEE the 33rd International Conference on Tools with Artificial Intelligenc, 2021: 619-623.
[20] 姜博,左万利,王英. 基于BERT的因果关系抽取[J]. 吉林大学学报(理学版),2021,59(6): 1439-1444.
[21] HUANG Z,XU W,YU K. Bidirectional LSTM-CRF models for sequence tagging[J]. arXiv preprint arXiv: 1508.01991,2015.
[22] 郑巧夺,吴贞东,邹俊颖.基于双层CNN-BiGRU-CRF的事件因果关系抽取[J]. 计算机工程,2021,47(5): 58-64,72.
[23] LI Z,LI Q,ZOU X,et al. Causality extraction based on self-attentive BiLSTM-CRF with transferred embeddings[J]. Neurocomputing,2021,423: 207-219.
[24] HOCHREITER S,SCHMIDHUBER J. Long short-term memory[J]. Neural Computation,1997,9(8): 1735-1780.
[25] GRAVES A,SCHMIDHUBER J. Framewise phoneme classification with bidirectional LSTM networks[C]//Proceedings of IEEE International Joint Conference on Neural Networks, 2005,4: 2047-2052.
[26] LAFFERTY J,MCCALLUM A,PEREIRA F C N. Conditional random fields: Probabilistic models for segmenting and labeling sequence data[C]//Proceedings of the 18th International Conference on Machine Learning, 2001: 282-289.
[27] FORNEY G D. The viterbi algorithm[J]. Proceedings of the IEEE,1973,61(3): 268-278.
[28] LI X, LI F,PAN L,et al. DuEE: A large-scale dataset for Chinese event extraction in real-world scenarios[C]//Proceedings of International Conference on Natural Language Processing and Chinese Computing,Springer,Cham,2020: 534-545.
[29] MIKOLOV T,SUTSKEVER I,CHEN K,et al. Distributed representations of words and phrases and their compositionality[C]//Proceedings of the 26th International Conference on Neural Information Processing Systems, 2013: 3111-3119.
[30] KINGMA D P,BA J. Adam: A method for stochastic optimization[C]//Proceedings of International Conference on Learning Representations, 2015: 1-15.
[31] 苗佳,段跃兴,张月琴,等. 基于CNN-BiGRU模型的事件触发词抽取方法[J]. 计算机工程,2021,47(9): 69-74.

基金

国家自然科学基金(61866029)
PDF(2672 KB)

1055

Accesses

0

Citation

Detail

段落导航
相关文章

/