DOI:10.19850/j.cnki.2096-4706.2023.07.003

基金项目：国家自然科学基金项目（62276091）；河南省重大公益专项（201300311200）

中图分类号：TP391                                        文献标识码：A                                   文章编号：2096-4706（2023）07-0011-05

An Entity Relationship Extraction Based on a Cascading Pointer Network—Research on Higher Education from the Perspective of New Engineering

LI Shilong1,2, ZHANG Haojun1,2, LI Daling1,2, WANG Jiahui 1,2, QI Chenyang1,2

(1.School of Information Science and Engineering, Henan University of Technology, Zhengzhou 450001, China; 2.Henan International Joint Laboratory of Grain Information Processing, Zhengzhou 450001, China)

Abstract: By artificially labeling the entity relationship of 252 typical educational research literatures on new engineering on CNKI, the experimental dataset NEDS (New Engineering Data Set) from the perspective of new engineering in the field of higher education is established, and a cascading pointer network model is designed. The experimental results show that the model performs well in NEDS in the field of higher education, and its accuracy, recall and F1 values reach 83.56, 76.25 and 79.74 respectively, and solve the problem of relationship overlap.

Keywords: new engineering; entity relationship extraction; cascading pointer; relationship overlap

参考文献：

[1] LAMPLE G，BALLESTEROS M，SUBRAMANIAN S，et al. Neural Architectures for Named Entity Recognition [J/OL].arXiv:1603.01360 [cs.CL].[2022-10-06].https://arxiv.org/abs/1603.01360v1.

[2] COLLOBERT R，WESTON J，BOTTOU L，et al. Natural Language Processing (almost) from Scratch [J].The Journal of Machine Learning Research，2011，12：2493-2537.

[3] CHIU J P C，NICHOLS E. Named Entity Recognition with Bidirectional LSTM-CNNs [J].Computer Science，2016，4：357-370.[4] SHEN Y Y，YUN H，LIPTON Z C，et al. Deep Active 

Learning for Named Entity Recognition [J/OL].arXiv:1707.05928 [cs. CL].[2022-10-06].https://arxiv.org/abs/1603.01360v1. 

[5] HUANG Z H，WEI X，KAI Y. Bidirectional LSTM-CRF Models for Sequence Tagging [J/OL].arXiv:1508.01991 [cs.CL].[2022-10-06].https://arxiv.org/abs/1508.01991.

[6] 闫雄、段跃兴、张泽华 . 采用自注意力机制和 CNN 融合的实体关系抽取 [J]. 计算机工程与科学，2020，42（11）：2059-2066.

[7] GAN T，GAN Y Q，HE Y M. Subsequence-Level Entity Attention LSTM for Relation Extraction [C]//2019 16th International Computer Conference on Wavelet Active Media Technology and Information Processing.Chengdu：IEEE，2019：262-265.

[8] MIWA M，BANSAL M. End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures [J/OL].arXiv:1601.00770 [cs. CL].[2022-10-06].https://arxiv.org/abs/1601.00770v2.

[9] 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.

[10] LI F， ZHANG M S，FU G H，et al. A neural joint model for entity and relation extraction from biomedical text [J/OL].BMC Bioinformatics，2017，18：1-11[2022-10-06].https://link.springer.com/content/pdf/10.1186/s12859-017-1609-9.pdf.

[11] ZHENG S C，WANG F，BAO H Y，et al. Joint Extraction of Entities and Relations Based on a Novel Tagging Scheme [J/OL].arXiv:1706.05075 [cs.CL].[2022-10-09].https://arxiv.org/abs/1706.05075v1.

[12] EBERTS M，ULGES A. An End-to-end Model for Entity-level Relation Extraction using Multi-instance Learning [J/OL].arXiv:2102.05980 [cs.CL].[2022-10-09].https://arxiv.org/abs/2102.05980v2.

[13] WEI Z P，SU J L，WANG Y，et al. A Novel Cascade Binary Tagging Framework for Relational Triple Extraction [C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.[S.I.]：Association for Computational Linguistics，2020：1476-1488.

[14] LIU Y H，OTT M，GOYAL N，et al. RoBERTa: A Robustly Optimized BERT Pretraining Approach [J/OL].arXiv:1907.11692 [cs. CL].[2022-10-09].https://arxiv.org/abs/1907.11692.

作者简介：李世龙（1997—），男，回族，河南平顶山人，硕士研究生在读，研究方向：自然语言处理；张浩军（1969—），男，汉族，浙江杭州人，博士，教授，硕士生导师，研究方向：人工智能；李大岭（1997—），男，汉族，河南濮阳人，硕士研究生在读，研究方向：自然语言处理；王家慧（1997—），女，汉族，河南开封人，硕士研究生在读，研究方向：光网络故障定位；齐晨阳（1998—），男，汉族，河南周口人，硕士研究生在读，研究方向：数据挖掘。