《计算机应用》唯一官方网站 ›› 2024, Vol. 44 ›› Issue (6): 1713-1719.DOI: 10.11772/j.issn.1001-9081.2023060818
所属专题: CCF第38届中国计算机应用大会 (CCF NCCA 2023)
• CCF第38届中国计算机应用大会 (CCF NCCA 2023) • 上一篇 下一篇
        
                    
            魏超1,2,3, 陈艳平1,2,3( ), 王凯1,2,3, 秦永彬1,2,3, 黄瑞章1,2,3
), 王凯1,2,3, 秦永彬1,2,3, 黄瑞章1,2,3
                  
        
        
        
        
    
收稿日期:2023-06-26
									
				
											修回日期:2023-08-16
									
				
											接受日期:2023-08-21
									
				
											发布日期:2023-08-30
									
				
											出版日期:2024-06-10
									
				
			通讯作者:
					陈艳平
							作者简介:魏超(1999—),男,贵州毕节人,硕士研究生,主要研究方向:自然语言处理、关系抽取基金资助:
        
                                                                                                                                            Chao WEI1,2,3, Yanping CHEN1,2,3( ), Kai WANG1,2,3, Yongbin QIN1,2,3, Ruizhang HUANG1,2,3
), Kai WANG1,2,3, Yongbin QIN1,2,3, Ruizhang HUANG1,2,3
			  
			
			
			
                
        
    
Received:2023-06-26
									
				
											Revised:2023-08-16
									
				
											Accepted:2023-08-21
									
				
											Online:2023-08-30
									
				
											Published:2024-06-10
									
			Contact:
					Yanping CHEN   
							About author:WEI Chao, born in 1999, M. S. candidate His research interests include natural language processing, relation extraction.Supported by:摘要:
针对关系抽取(RE)任务中实体关系语义挖掘困难和预测关系有偏差等问题,提出一种基于掩码提示与门控记忆网络校准(MGMNC)的RE方法。首先,利用提示中的掩码学习实体之间在预训练语言模型(PLM)语义空间中的潜在语义,通过构造掩码注意力权重矩阵,将离散的掩码语义空间相互关联;其次,采用门控校准网络将含有实体和关系语义的掩码表示融入句子的全局语义;再次,将它们作为关系提示校准关系信息,随后将句子表示的最终表示映射至相应的关系类别;最后,通过更好地利用提示中掩码,并结合传统微调方法的学习句子全局语义的优势,充分激发PLM的潜力。实验结果表明,所提方法在SemEval(SemEval-2010 Task 8)数据集的F1值达到91.4%,相较于RELA(Relation Extraction with Label Augmentation)生成式方法提高了1.0个百分点;在SciERC(Entities, Relations, and Coreference for Scientific knowledge graph construction)和CLTC(Chinese Literature Text Corpus)数据集上的F1值分别达到91.0%和82.8%。所提方法在上述3个数据集上均明显优于对比方法,验证了所提方法的有效性。相较于基于生成式的方法,所提方法实现了更优的抽取性能。
中图分类号:
魏超, 陈艳平, 王凯, 秦永彬, 黄瑞章. 基于掩码提示与门控记忆网络校准的关系抽取方法[J]. 计算机应用, 2024, 44(6): 1713-1719.
Chao WEI, Yanping CHEN, Kai WANG, Yongbin QIN, Ruizhang HUANG. Relation extraction method based on mask prompt and gated memory network calibration[J]. Journal of Computer Applications, 2024, 44(6): 1713-1719.
| 超参数 | 实验设置 | 超参数 | 实验设置 | 
|---|---|---|---|
| PLM | RoBERTa_LARGE | 迭代次数 | 20 | 
| 学习率 | 10-5 | 失活率 | 0.1 | 
| 最大句长 | 128/512 | 随机种子数 | 314 159 | 
| 训练批次 | 32 | 
表1 超参数设置
Tab. 1 Hyperparameter settings
| 超参数 | 实验设置 | 超参数 | 实验设置 | 
|---|---|---|---|
| PLM | RoBERTa_LARGE | 迭代次数 | 20 | 
| 学习率 | 10-5 | 失活率 | 0.1 | 
| 最大句长 | 128/512 | 随机种子数 | 314 159 | 
| 训练批次 | 32 | 
| 方法 | P | R | F1 | 
|---|---|---|---|
| CR-CNN | 83.7 | 84.7 | 84.1 | 
| Multi-Channel | — | — | 84.6 | 
| MixCNN | 83.1 | 86.6 | 84.8 | 
| TACNN | — | — | 85.3 | 
| TRE | 88.0 | 86.2 | 87.1 | 
| PTR | 88.4 | 89.8 | 89.1 | 
| KnowPrompt | — | — | 90.2 | 
| RELA | — | — | 90.4 | 
| Indicator-aware | 90.6 | 90.1 | 90.4 | 
| KLG | — | — | 90.5 | 
| SPOT | 89.9 | 91.4 | 90.6 | 
| CPA | 91.4 | 90.2 | 90.8 | 
| MGMNC | 90.8 | 92.0 | 91.4 | 
表2 各方法在SemEval数据集上的实验结果 (%)
Tab. 2 Experimental results of various methods on SemEval dataset
| 方法 | P | R | F1 | 
|---|---|---|---|
| CR-CNN | 83.7 | 84.7 | 84.1 | 
| Multi-Channel | — | — | 84.6 | 
| MixCNN | 83.1 | 86.6 | 84.8 | 
| TACNN | — | — | 85.3 | 
| TRE | 88.0 | 86.2 | 87.1 | 
| PTR | 88.4 | 89.8 | 89.1 | 
| KnowPrompt | — | — | 90.2 | 
| RELA | — | — | 90.4 | 
| Indicator-aware | 90.6 | 90.1 | 90.4 | 
| KLG | — | — | 90.5 | 
| SPOT | 89.9 | 91.4 | 90.6 | 
| CPA | 91.4 | 90.2 | 90.8 | 
| MGMNC | 90.8 | 92.0 | 91.4 | 
| 方法 | F1 | 方法 | F1 | 
|---|---|---|---|
| CNN | 52.4 | SR-BRCNN | 65.9 | 
| CR-CNN | 54.1 | BERT-CNN | 77.1 | 
| BRCNN | 55.6 | MGMNC | 82.8 | 
表3 各方法在CLTC数据集上的实验结果 (%)
Tab.3 Experimental results of various methods on CLTC dataset
| 方法 | F1 | 方法 | F1 | 
|---|---|---|---|
| CNN | 52.4 | SR-BRCNN | 65.9 | 
| CR-CNN | 54.1 | BERT-CNN | 77.1 | 
| BRCNN | 55.6 | MGMNC | 82.8 | 
| 模型 | SemEval | SciERC | ||||
|---|---|---|---|---|---|---|
| P | R | F1 | P | R | F1 | |
| REBEL | — | — | 82.0 | — | — | 86.3 | 
| RELA | — | — | 90.4 | — | — | 90.3 | 
| MGMNC | 90.8 | 92.0 | 91.4 | 90.7 | 91.3 | 91.0 | 
表4 MGMNC与生成模型的对比实验结果 (%)
Tab. 4 Comparison experiment results between MGMNC and generative models
| 模型 | SemEval | SciERC | ||||
|---|---|---|---|---|---|---|
| P | R | F1 | P | R | F1 | |
| REBEL | — | — | 82.0 | — | — | 86.3 | 
| RELA | — | — | 90.4 | — | — | 90.3 | 
| MGMNC | 90.8 | 92.0 | 91.4 | 90.7 | 91.3 | 91.0 | 
| 关系类别 | PTR | MGMNC | ||||
|---|---|---|---|---|---|---|
| P | R | F1 | P | R | F1 | |
| Component‑Whole | 90.03 | 86.86 | 88.42 | 89.46 | 89.74 | 89.60 | 
| Instrument‑Agency | 87.67 | 82.05 | 84.77 | 88.16 | 85.90 | 87.01 | 
| Member‑Collection | 86.08 | 87.55 | 86.81 | 88.61 | 90.13 | 89.36 | 
| Cause‑Effect | 90.99 | 95.43 | 93.15 | 92.35 | 95.73 | 94.01 | 
| Entity‑Destination | 90.49 | 94.52 | 92.46 | 93.65 | 95.89 | 94.75 | 
| Content‑Container | 89.84 | 87.50 | 88.65 | 92.82 | 94.27 | 93.54 | 
| Message‑Topic | 89.86 | 95.02 | 92.36 | 92.37 | 92.72 | 92.54 | 
| Product‑Producer | 83.92 | 92.64 | 88.07 | 90.17 | 91.34 | 90.75 | 
| Entity‑Origin | 88.35 | 85.27 | 86.79 | 88.42 | 88.76 | 88.59 | 
表5 MGMNC与PTR在各关系类别间性能对比 (%)
Tab. 5 Performance comparison between MGMNC amd PTR on various relation classes
| 关系类别 | PTR | MGMNC | ||||
|---|---|---|---|---|---|---|
| P | R | F1 | P | R | F1 | |
| Component‑Whole | 90.03 | 86.86 | 88.42 | 89.46 | 89.74 | 89.60 | 
| Instrument‑Agency | 87.67 | 82.05 | 84.77 | 88.16 | 85.90 | 87.01 | 
| Member‑Collection | 86.08 | 87.55 | 86.81 | 88.61 | 90.13 | 89.36 | 
| Cause‑Effect | 90.99 | 95.43 | 93.15 | 92.35 | 95.73 | 94.01 | 
| Entity‑Destination | 90.49 | 94.52 | 92.46 | 93.65 | 95.89 | 94.75 | 
| Content‑Container | 89.84 | 87.50 | 88.65 | 92.82 | 94.27 | 93.54 | 
| Message‑Topic | 89.86 | 95.02 | 92.36 | 92.37 | 92.72 | 92.54 | 
| Product‑Producer | 83.92 | 92.64 | 88.07 | 90.17 | 91.34 | 90.75 | 
| Entity‑Origin | 88.35 | 85.27 | 86.79 | 88.42 | 88.76 | 88.59 | 
| GMN | MAM | P | R | F1 | 
|---|---|---|---|---|
| × | × | 88.8 | 90.8 | 89.7 | 
| × | √ | 90.2 | 90.8 | 90.4 | 
| √ | × | 90.3 | 91.5 | 90.9 | 
| √ | √ | 90.8 | 92.0 | 91.4 | 
表6 消融实验结果 (%)
Tab. 6 Ablation experiment results
| GMN | MAM | P | R | F1 | 
|---|---|---|---|---|
| × | × | 88.8 | 90.8 | 89.7 | 
| × | √ | 90.2 | 90.8 | 90.4 | 
| √ | × | 90.3 | 91.5 | 90.9 | 
| √ | √ | 90.8 | 92.0 | 91.4 | 
| 设置 | P | R | F1 | 
|---|---|---|---|
| 无GMN | 90.2 | 90.8 | 90.4 | 
| 单GMN | 89.5 | 92.5 | 91.0 | 
| 双GMN | 90.8 | 92.0 | 91.4 | 
表7 GMN校准对比结果 (%)
Tab. 7 Comparison results of GMN calibration
| 设置 | P | R | F1 | 
|---|---|---|---|
| 无GMN | 90.2 | 90.8 | 90.4 | 
| 单GMN | 89.5 | 92.5 | 91.0 | 
| 双GMN | 90.8 | 92.0 | 91.4 | 
| 1 | ZHOU G D, SU J, ZHANG J, et al. Exploring various knowledge in relation extraction [C]// Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics. Stroudsburg: ACL, 2005: 427-434. | 
| 2 | DEVLIN J, CHANG M-W, LEE K, et al. BERT: pre-training of deep bidirectional transformers for language understanding [C]// Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics. Stroudsburg: ACL, 2019: 4471-4186. | 
| 3 | LIU Y, OTT M, GOYAL N, et al. RoBERTa: a robustly optimized bert pretraining approach [EB/OL]. [2023-07-27]. . | 
| 4 | CHEN Y, YANG W, WANG K, et al. A neuralized feature engineering method for entity relation extraction [J]. Neural Network, 2021, 141: 249-260. | 
| 5 | ZHOU W, CHEN M. An improved baseline for sentence-level relation extraction [C]// Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers). Stroudsburg: ACL, 2022: 161-168. | 
| 6 | QIN Y, YANG W, WANG K, et al. Entity relation extraction based on entity indicators [J]. Symmetry, 2021, 13(4): 539. | 
| 7 | 龚汝鑫,余肖生.基于BERT-BILSTM的医疗文本关系提取方法[J]. 计算机技术与发展,2022,32(4):186-192. | 
| GONG R X, YU X S. Relation extraction method of medical texts based on BERT-BILSTM [J]. Computer Technology and Development, 2022, 32(4): 186-192. | |
| 8 | SCHICK T, SCHÜTZE H. Exploiting cloze-questions for few-shot text classification and natural language inference [C]// Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume. Stroudsburg: ACL, 2021: 255-269. | 
| 9 | TAM D, MENON R R, BANSAL M, et al. Improving and simplifying pattern exploiting training [C]// Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: ACL, 2021: 4980-4991. | 
| 10 | LI D, HU B, CHEN Q. Prompt-based text entailment for low-resource named entity recognition [C]// Proceedings of the 29th International Conference on Computational Linguistics.[S.l.]: International Committee on Computational Linguistics, 2022: 1896-1903. | 
| 11 | LIU P, YUAN W, FU J, et al. Pre-train, prompt, and predict: a systematic survey of prompting methods in natural language processing [J]. ACM Computing Surveys, 2023, 55(9): 195. | 
| 12 | CHEN Y, ZHENG Q, CHEN P. Feature assembly method for extracting relations in Chinese [J]. Artificial Intelligence, 2015, 228: 179-194. | 
| 13 | ZHAO S, GRISHMAN R. Extracting relations with integrated information using kernel methods [C]// Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics. Stroudsburg: ACL, 2005: 419-426. | 
| 14 | ZENG D, LIU K, LAI S, et al. Relation classification via convolutional deep neural network [C]// Proceedings of 25th International Conference on Computational Linguistics. Stroudsburg: ACL, 2014: 2335-2344. | 
| 15 | GENG Z Q, CHEN G F, HAN Y M, et al. Semantic relation extraction using sequential and tree-structured LSTM with attention [J]. Information Sciences, 2020, 509: 183-192. | 
| 16 | BROWN T, MANN B, RYDER N, et al. Language models are few-shot learners [C]// Proceedings of the 34th International Conference on Neural Information Processing Systems. Red Hook: Curran Associates, 2020: 1877-1901. | 
| 17 | 武小平,张强,赵芳.基于BERT的心血管医疗指南实体关系抽取方法[J].计算机应用,2021,41(1):145-149. | 
| WU X P, ZHANG Q, ZHAO F. Entity relation extraction method for guidelines of cardiovascular disease based on bidirectional encoder representation from transformers [J]. Journal of Computer Applications, 2021, 41(1): 145-149. | |
| 18 | LI R, LI D, YANG J, et al. Joint extraction of entities and relations via an entity correlated attention neural model [J]. Information Sciences, 2021, 581: 179-193. | 
| 19 | ZHAO W, ZHAO S, CHEN S, et al. Entity and relation collaborative extraction approach based on multi-head attention and gated mechanism [J]. Connection Science, 2022, 34(1): 670-686. | 
| 20 | 杨卫哲,秦永彬,黄瑞章,等.面向中文关系抽取的句子结构获取方法[J]. 数据采集与处理,2021,36(3):605-620. | 
| YANG W Z, QIN Y B, HUANG R Z, et al.Sentence structure acquisition method for Chinese relation extraction [J]. Journal of Data Acquisition & Processing, 2021, 36(3): 605-620. | |
| 21 | HAN X, ZHAO W, DING N, et al. PTR: prompt tuning with rules for text classification [J]. AI Open, 2022, 3: 182-192. | 
| 22 | GAO T Y, FISCH A, CHEN D Q. Making pre-trained language models better few-shot learners [C]// Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Stroudsburg: ACL, 2021: 3816-3830. | 
| 23 | SHIN T, RAZEGHI Y, ROBERT L, et al. AutoPrompt: eliciting knowledge from language models with automatically generated prompts [C]// Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: ACL, 2020: 4222-4235. | 
| 24 | WANG K, CHEN Y, WEN K, et al. Cue prompt adapting model for relation extraction [J]. Connection Science, 2022, 35(1): 2161478. | 
| 25 | CHO K, VAN MERRIËNBOER B, GULCEHRE C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation [C]// Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: ACL, 2014: 1724-1734. | 
| 26 | LIU Y, HU J, WAN X, et al. Learn from relation information: towards prototype representation rectification for few-shot relation extraction [C]// Findings of the Association for Computational Linguistics, NAACL 2022. Stroudsburg: ACL, 2022: 1822-1831. | 
| 27 | HENDRICKX I, KIM S N, KOZAREVA Z, et al. SemEval-2010 task 8: multi-way classification of semantic relations between pairs of nominals [C]// Proceedings of the 5th International Workshop on Semantic Evaluation. Stroudsburg: ACL, 2010: 33-38. | 
| 28 | XU J, WEN J, SUN X, et al. A discourse-level named entity recognition and relation extraction dataset for Chinese literature text [EB/OL].[2023-07-27].. | 
| 29 | LUAN Y, HE L, OSTENDORG M, et al. Multi-task identification of entities, relations, and coreference for scientific knowledge graph construction [C]// Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: ACL, 2018: 3219-3232. | 
| 30 | DOS SANTOS C, XIANG B, ZHOU B. Classifying relations by ranking 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 1: Long Papers). Stroudsburg: ACL, 2015: 626-634. | 
| 31 | CHEN Y, WANG K, YANG W, et al. A multi-channel deep neural network for relation extraction [J]. IEEE Access, 2020, 8: 13195-13203. | 
| 32 | ZHENG S, XU J, ZHOU P, et al. A neural network framework for relation extraction: learning entity semantic and relation pattern [J]. Knowledge-Based Systems, 2016, 114: 12-23. | 
| 33 | GENG Z, LI J, HAN Y, et al. Novel target attention convolutional neural network for relation classification [J]. Information Sciences, 2022, 597: 24-37. | 
| 34 | ALT C, HÜBNER M, HENNIG L. Improving relation extraction by pre-trained language representations [EB/OL]. [2023-07-27]. . | 
| 35 | CHEN X, ZHANG N, XIE X, et al. KnowPrompt: knowledge-aware prompt-tuning with synergistic optimization for relation extraction [C]// Proceedings of the ACM Web Conference 2022. New York: ACM, 2022: 2778-2788. | 
| 36 | LI B, YU D, YE W, et al. Sequence generation with label augmentation for relation extraction [EB/OL]. [2023-07-27]. . | 
| 37 | TAO Q, LUO X, WANG H. Enhancing relation extraction using syntactic indicators and sentential contexts [C]// Proceedings of the 2019 IEEE 31st International Conference on Tools with Artificial Intelligence. Piscataway: IEEE, 2019: 1574-1580. | 
| 38 | LI B, YE W, ZHANG J, et al. Reviewing labels: label graph network with top-k prediction set for relation extraction [EB/OL]. [2023-07-27]. . | 
| 39 | LI J, KATSIS Y, BALDWIN T, et al. SPOT: knowledge-enhanced language representations for information extraction [C]// Proceedings of the 31st ACM International Conference on Information & Knowledge Management. New York: ACM, 2022: 1124-1134. | 
| 40 | CAI R, ZHANG X, WANG H. Bidirectional recurrent convolutional neural network for relation classification [C]// Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Stroudsburg: ACL, 2016: 756-765. | 
| 41 | WEN J, SUN X, REN X, et al. Structure regularized neural network for entity relation classification for chinese literature text [C]// Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers). Stroudsburg: ACL, 2018: 365-370. | 
| 42 | HUGUET CABOT P-L, NAVIGLI R. REBEL: relation extraction by end-to-end language generation [C]// Findings of the Association for Computational Linguistics: EMNLP 2021. Stroudsburg: ACL, 2021: 2370-2381. | 
| [1] | 吴相岚, 肖洋, 刘梦莹, 刘明铭. 基于语义增强模式链接的Text-to-SQL模型[J]. 《计算机应用》唯一官方网站, 2024, 44(9): 2689-2695. | 
| [2] | 赵宇博, 张丽萍, 闫盛, 侯敏, 高茂. 基于改进分段卷积神经网络和知识蒸馏的学科知识实体间关系抽取[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2421-2429. | 
| [3] | 邓凯丽, 魏伟波, 潘振宽. 改进掩码自编码器的工业缺陷检测方法[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2595-2603. | 
| [4] | 唐媛, 陈艳平, 扈应, 黄瑞章, 秦永彬. 基于多尺度混合注意力卷积神经网络的关系抽取模型[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2011-2017. | 
| [5] | 游新冬, 问英姿, 佘鑫鹏, 吕学强. 面向煤矿机电设备领域的三元组抽取方法[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2026-2033. | 
| [6] | 毛典辉, 李学博, 刘峻岭, 张登辉, 颜文婧. 基于并行异构图和序列注意力机制的中文实体关系抽取模型[J]. 《计算机应用》唯一官方网站, 2024, 44(7): 2018-2025. | 
| [7] | 余新言, 曾诚, 王乾, 何鹏, 丁晓玉. 基于知识增强和提示学习的小样本新闻主题分类方法[J]. 《计算机应用》唯一官方网站, 2024, 44(6): 1767-1774. | 
| [8] | 沈君凤, 周星辰, 汤灿. 基于改进的提示学习方法的双通道情感分析模型[J]. 《计算机应用》唯一官方网站, 2024, 44(6): 1796-1806. | 
| [9] | 袁泉, 陈昌平, 陈泽, 詹林峰. 基于BERT的两次注意力机制远程监督关系抽取[J]. 《计算机应用》唯一官方网站, 2024, 44(4): 1080-1085. | 
| [10] | 郭安迪, 贾真, 李天瑞. 基于伪实体数据增强的高精准率医学领域实体关系抽取[J]. 《计算机应用》唯一官方网站, 2024, 44(2): 393-402. | 
| [11] | 高颖杰, 林民, 斯日古楞null, 李斌, 张树钧. 基于片段抽取原型网络的古籍文本断句标点提示学习方法[J]. 《计算机应用》唯一官方网站, 2024, 44(12): 3815-3822. | 
| [12] | 颜新月, 杨淑群, 高永彬. 基于证据增强与多特征融合的文档级关系抽取[J]. 《计算机应用》唯一官方网站, 2024, 44(11): 3379-3385. | 
| [13] | 邓金科, 段文杰, 张顺香, 汪雨晴, 李书羽, 李嘉伟. 基于提示增强与双图注意力网络的复杂因果关系抽取[J]. 《计算机应用》唯一官方网站, 2024, 44(10): 3081-3089. | 
| [14] | 于碧辉, 蔡兴业, 魏靖烜. 基于提示学习的小样本文本分类方法[J]. 《计算机应用》唯一官方网站, 2023, 43(9): 2735-2740. | 
| [15] | 齐爱玲, 王宣淋. 基于中层细微特征提取与多尺度特征融合细粒度图像识别[J]. 《计算机应用》唯一官方网站, 2023, 43(8): 2556-2563. | 
| 阅读次数 | ||||||
| 全文 |  | |||||
| 摘要 |  | |||||