1School of Management, Nanjing University of Posts and Telecommunications, Nanjing 210003, China 2School of Internet of Things, Nanjing University of Posts and Telecommunications, Nanjing 210003, China 3Key Research Base of Philosophy and Social Sciences in Jiangsu-Information Industry Integration Innovation and Emergency Management Research Center, Nanjing 210003, China
[Objective] This paper aims to improve the accuracy of event detection tasks by fusing semantic information. [Methods] First, we stored the non-relational semantic information with an initial word vector and encoded them with the Bi-LSTM model to aggregate their contexts. Then, we developed a relation graph based on relational semantic information. Third, we used a multi-scale convolutional neural network to capture the spatial information from the adjacency matrix and fuse it with the word vector. Finally, we built a Gate-GCN model to aggregate relational semantic information between adjacent word vectors to enhance their representation ability. [Results] We examined the new model with the ACE05 benchmark dataset. Our method’s F1 value reached 76.3%, which was 1.2% higher than the existing mainstream models. [Limitations] The proposed model needs to be validated with general datasets. [Conclusions] Fusion of multiple types of semantic information can effectively improve the event detection performance.
魏建香, 陆谦, 韩普, 黄卫东. 基于多语义信息融合的事件检测模型*[J]. 数据分析与知识发现, 2023, 7(12): 64-74.
Wei Jianxiang, Lu Qian, Han Pu, Huang Weidong. Event Detection Model Based on Semantic Information Fusion. Data Analysis and Knowledge Discovery, 2023, 7(12): 64-74.
S1：North Korea’s military may have fired a loser at a U.S helicopter.
Words North Korea’s military U.S
Entity types PER：Group GPE：Nation
Words North Korea’s military Loser helicopter
Event arguments Attacker Instrument Target
Trigger：fired
Event type：Attack
Table 1 包含多类语义信息的事件检测例句
Fig.1 基于多语义信息融合的事件检测模型结构
Fig.2 关系图与邻接矩阵
超参数名
参数值
超参数名
参数值
初始词向量维度
100
批量大小
30
事件要素向量维度
100
最大句子长度
50
实体类型向量维度
25
Bi-LSTM层数
1
关系类型向量维度
50
GCN层数
2
Bi-LSTM隐藏层维度
100
学习率
0.1
GCN隐藏层维度
200
偏置项参数α
5
Table 2 模型的超参数设置
网络层
FLOPs
Params
CNN
9.02MMac
22.55k
Bi-LSTM
6.07MMac
301.6k
Gated-GCN
11.6MMac
52.75k
Table 3 模型复杂度分析
模型
P/%
R/%
F1/%
Cross-entity
72.9
64.3
68.3
MaxEntropy
74.5
59.1
65.9
PSL
75.3
64.4
69.4
DMCNN
75.6
63.6
69.1
JRNN
66.0
73.0
69.3
ANN
78.0
66.3
71.7
GCN-ED
77.9
68.8
73.1
JMEE
76.3
71.3
73.7
SELF
71.3
74.7
73.0
BGCN AD-DMBERT
77.5 77.9
72.4 72.5
74.2 75.1
本文
76.0
76.7
76.3
Table 4 模型性能对比
特征组合
P/%
R/%
F1/%
词向量表示： 关系表示：
69.7
70.6
70.1
词向量表示： 关系表示：
71.1
74.1
72.5
词向量表示： 关系表示：
76.6
73.5
75.0
Table 5 不同特征组合的性能比较
模型
P/%
R/%
F1/%
Bi-LSTM+GCN
76.6
73.5
75.0
CNN+Bi-LSTM+GCN
77.0
74.3
75.6
Table 6 融合空间信息的模型性能
模型
P/%
R/%
F1/%
CNN+Bi-LSTM+GCN
77.0
74.3
75.6
CNN+Bi-LSTM+Gated-GCN
76.0
76.7
76.3
Table 7 使用Gated-GCN的模型性能
Fig.3 基于8个大类分类的混淆矩阵
Fig.4 基于34个小类分类的混淆矩阵（部分）
Fig.5 基准模型的测试结果混淆矩阵
Fig.6 本文模型的测试结果混淆矩阵
[1]
Doddington G, Mitchell A, Przybocki M. The Automatic Content Extraction (ACE) Program—Tasks, Data, and Evaluation[C]// Proceedings of the 4th International Conference on Language Resources and Evaluation. 2004: 837-840.
[2]
Li L, Jin L, Zhang Z Q, et al. Graph Convolution over Multiple Latent Context-Aware Graph Structures for Event Detection[J]. IEEE Access, 2020, 8: 171435-171446.
doi: 10.1109/Access.6287639
[3]
Dutta S, Ma L, Saha T K, et al. GTN-ED: Event Detection Using Graph Transformer Networks[C]// Proceedings of the 15th Workshop on Graph-Based Methods for Natural Language Processing. 2021: 132-137.
(Wan Qizhi, Wan Changxuan, Hu Rong, et al. Chinese Financial Event Extraction Base on Syntactic and Semantic Dependency Parsing[J]. Chinese Journal of Computers, 2021, 44 (3): 508-530.)
(Chen Jiali, Hong Yu, Wang Jie, et al. Combination of Dependency and Semantic Information via Gated Mechanism for Event Detection[J]. Journal of Chinese Information Processing, 2020, 34(8): 51-60.)
[6]
Cui Z C, Chen W L, Chen Y X. Multi-Scale Convolutional Neural Networks for Time Series Classification[OL]. arXiv Preprint, arXiv: 1603.06995.
[7]
Kipf T N, Welling M. Semi-Supervised Classification with Graph Convolutional Networks[OL]. arXiv Preprint, arXiv: 1609.02907.
[8]
Dauphin Y N, Fan A, Auli M, et al. Language Modeling with Gated Convolutional Networks[C]// Proceedings of the 34th International Conference on Machine Learning - Volume 70. 2017: 933-941.
[9]
Grishman R, Westbrook D, Meyers A. NYU’s English ACE 2005 System Description[C]// Proceedings of ACE 2005 Evaluation Workshop. 2005.
[10]
Ji H, Grishman R. Refining Event Extraction Through Cross-Document Inference[C]// Proceedings of ACL-08:HLT. 2008: 254-262.
[11]
Liao S S, Grishman R. Using Document Level Cross-Event Inference to Improve Event Extraction[C]// Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics. 2010: 789-797.
[12]
Hong Y, Zhang J F, Ma B, et al. Using Cross-Entity Inference to Improve Event Extraction[C]// Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies-Volume 1. 2011: 1127-1136.
[13]
Nguyen T H, Grishman R. Event Detection and Domain Adaptation with Convolutional Neural Networks[C]// Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2:Short Papers). 2015: 365-371.
[14]
Chen Y B, Xu L H, Liu K, et al. Event Extraction via Dynamic Multi-Pooling Convolutional Neural Networks[C]// Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1:Long Papers). 2015: 167-176.
[15]
Nguyen T H, Cho K, Grishman R. Joint Event Extraction via Recurrent Neural Networks[C]// Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies. 2016: 300-309.
[16]
Feng X C, Qin B, Liu T. A Language-Independent Neural Network for Event Detection[J]. Science China Information Sciences, 2018, 61(9): 092106.
doi: 10.1007/s11432-017-9359-x
[17]
Sha L, Qian F, Chang B B, et al. Jointly Extracting Event Triggers and Arguments by Dependency-Bridge RNN and Tensor-Based Argument Interaction[C]// Proceedings of the 32nd AAAI Conference on Artificial Intelligence and the 30th Innovative Applications of Artificial Intelligence Conference and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence. 2018: 5916-5923.
[18]
Orr J W, Tadepalli P, Fern X. Event Detection with Neural Networks: A Rigorous Empirical Evaluation[OL]. arXiv Preprint, arXiv:1808.08504.
[19]
Nguyen T H, Grishman R. Graph Convolutional Networks with Argument-Aware Pooling for Event Detection[C]// Proceedings of the 32nd AAAI Conference on Artificial Intelligence and the 30th Innovative Applications of Artificial Intelligence Conference and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence. 2018: 5900-5907.
[20]
Liu X, Luo Z C, Huang H Y. Jointly Multiple Events Extraction via Attention-Based Graph Information Aggregation [OL]. arXiv Preprint, arXiv:1809.09078.
[21]
Yan H R, Jin X L, Meng X B, et al. Event Detection with Multi-Order Graph Convolution and Aggregated Attention[C]// Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. 2019: 5766-5770.
[22]
Cui S Y, Yu B W, Liu T W, et al. Edge-Enhanced Graph Convolution Networks for Event Detection with Syntactic Relation[OL]. arXiv Preprint, arXiv: 2020.10757.
[23]
Devlin J, Chang M W, Lee K, et al. BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding[OL]. arXiv Preprint, arXiv: 1810.04805.
[24]
Wang X Z, Wang Z Q, Han X, et al. HMEAE: Hierarchical Modular Event Argument Extraction[C]// Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. 2019: 5777-5783.
[25]
Walker C, Strassel S, Medero J, et al. ACE 2005 Multilingual Training Corpus[OL]. Philadelphia: Linguistic Data Consortium, 2006. https://doi.org/10.35111/mwxc-vh88.
[26]
LeCun Y, Bottou L, Bengio Y, et al. Gradient-Based Learning Applied to Document Recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
doi: 10.1109/5.726791
[27]
Mikolov T, Chen K, Corrado G, et al. Efficient Estimation of Word Representations in Vector Space[OL]. arXiv Preprint, arXiv:1301.3781.
[28]
Zhang S, Zheng D Q, Hu X C, 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.
[29]
Chen Y B, Yang H, Liu K, et al. Collective Event Detection via a Hierarchical and Bias Tagging Networks with Gated Multi-Level Attention Mechanisms[C]// Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. 2018: 1267-1276.
[30]
Li Q, Ji H, Huang L. Joint Event Extraction via Structured Prediction with Global Features[C]// Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1:Long Papers). 2013: 73-82.
[31]
Liu S L, Liu K, He S Z, et al. A Probabilistic Soft Logic Based Approach to Exploiting Latent and Global Information in Event Classification[C]// Proceedings of the 30th AAAI Conference on Artificial Intelligence. 2016: 2993-2999.
[32]
Liu S L, Chen Y B, Liu K, et al. Exploiting Argument Information to Improve Event Detection via Supervised Attention Mechanisms[C]// Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1:Long Papers). 2017: 1789-1798.
[33]
Hong Y, Zhou W X, Zhang J L, et al. Self-Regulation: Employing a Generative Adversarial Network to Improve Event Detection[C]// Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1:Long Papers). 2018: 515-526.
(Cheng Siwei, Ge Weiyi, Wang Yu, et al. BGCN: Trigger Detection Based on BERT and Graph Convolution Network[J]. Computer Science, 2021, 48(7): 292-298.)
doi: 10.11896/jsjkx.200500133
[35]
Wang X Z, Han X, Liu Z Y, et al. Adversarial Training for Weakly Supervised Event Detection[C]// Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies, Volume 1 (Long and Short Papers). 2019: 998-1008.
