| 205 | 5 | 213 |
| 下载次数 | 被引频次 | 阅读次数 |
针对文本中深层语义难以计算的问题，提出了基于句法依存关系的多头图注意力实体关系联合抽取模型和融合层次类型的文档相似性匹配。首先通过多头图注意力网络对文本进行实体关系抽取，然后设计融合层次类型的词移距离相似性计算方法以及基于图相似的文档相似性计算模型，利用文档中的实体和关系构建图结构，根据图级特征进行相似性计算。最后，通过对比实验验证了所提方法在文档相似性计算、图相似度计算和图分类任务中的有效性。
Abstract：Aiming at the difficulty to mine deep semantics in text, a multi-head graph attention entity-relation joint extraction model based on syntactic dependencies and a fusion hierarchical type of document similarity matching were proposed. Firstly, the entity relation extraction was carried out on the text through the multi-head graph attention network. Then, the word shift distance similarity calculation method of fusion hierarchical type and the document similarity calculation model based on graph similarity were designed, and the graph structure was constructed by using the entities and relations in the document. Thus, the features representing the graph level were obtained for similarity calculation. Finally, the effectiveness of the proposed method in document similarity calculation, graph similarity calculation and graph classification tasks was verified by comparative experiments.
[1]董星彤，陈士宏，陈淑鑫．自然语言处理文本查重优化算法设计[J]．科学技术与工程，2022,22(3):1091-1097.DONG X T,CHEN S H,CHEN S X.Algorithm design of text duplicated-checking based on natural language processing[J].Science technology and engineering,2022,22(3):1091-1097．
[2]鄂海红，张文静，肖思琪，等．深度学习实体关系抽取研究综述[J]．软件学报，2019,30(6):1793-1818.E H H,ZHANG W J,XIAO S Q,et al.Survey of entity relationship extraction based on deep learning[J].Journal of software,2019,30(6):1793-1818．
[3]李冬梅，张扬，李东远，等．实体关系抽取方法研究综述[J]．计算机研究与发展，2020,57(7):1424-1448.LI D M,ZHANG Y,LI D Y,et al.Review of entity relation extraction methods[J].Journal of computer research and development,2020,57(7):1424-1448．
[4]ZENG D J,LIU K,CHEN Y B,et al.Distant supervision for relation extraction via piecewise convolutional neural networks[C]∥Proceedings of the Conference on Empirical Methods in Natural Language Processing.Stroudsburg:Association for Computational Linguistics,2015:1753-1762．
[5]ZHONG Z X,CHEN D Q.A frustratingly easy approach for entity and relation extraction[C]∥Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.Stroudsburg:Association for Computational Linguistics,2021:50-61．
[6]ZHENG S C,HAO Y X,LU D Y,et al.Joint entity and relation extraction based on a hybrid neural network[J].Neurocomputing,2017,257:59-66．
[7]陈观林，侍晓龙，周梁，等．基于深度强化学习的文本相似语义计算模型[J]．郑州大学学报(理学版)，2020,52(3):1-8.CHEN G L,SHI X L,ZHOU L,et al.A text similarity semantic computing model based on deep reinforcement learning[J].Journal of Zhengzhou university(natural science edition),2020,52(3):1-8．
[8]CHANDRASEKARAN D,MAGO V.Evolution of semantic similarity:a survey[J].ACM computing surveys,2022,54(2):1-37．
[9]KUSNER M J,SUN Y,KOLKIN N I,et al.From word embeddings to document distances[C]∥Proceedings of the 32nd International Conference on Machine Learning.New York:ACM Press,2015,37:957-966．
[10]PAN X W,HUANG P,LI S,et al.MCRWR:a new method to measure the similarity of documents based on semantic network[J].BMC bioinformatics,2022,23(1):56．
[11]AHMADZADEH E,KIM H,JEONG O,et al.A deep bidirectional LSTM-GRU network model for automated ciphertext classification[J].IEEE access,2022,10:3228-3237．
[12]VELICKOVIC'P,CUCURULL G,CASANOVA A,et al.Graph attention networks[EB/OL].(2017-10-30)[2022-03-30].https:∥doi.org/10.48550/ar Xiv.1710.10903．
[13]FU C Z,LIU C R,ISHI C T,et al.Multi-modality emotion recognition model with GAT-based multi-head intermodality attention[J].Sensors,2020,20(17):4894．
[14]XIE R,LIU Z,SUN M.Representation learning of knowledge graphs with hierarchical types[C]∥25th International Joint Conference on Artificial Intelligence.Amsterdam:Elsevier Press,2016:2965-2971．
[15]BOUDAA T,MAROUANI M E,ENNEYA N.Using earth mover's distance and machine learning for recognizing textual entailment in Arabic[J].Computación y sistemas,2020,24(4):1499-1508.
基本信息:
DOI：10.13705/j.issn.1671-6841.2022159
中图分类号:TP391.1;TP183
引用信息:
[1]赵文彬,王佳琦,吴峰,等.基于图神经网络文档相似度的实体与关系层次匹配方法[J],2023,55(06):8-14.DOI:10.13705/j.issn.1671-6841.2022159.
基金信息:
国家自然科学基金项目(61373160);; 河北省自然科学基金项目(F2021210003);; 河北省教育厅青年基金项目(QN2020197)