当前位置>主页 > 期刊在线 > 信息化应用 >

信息化应用22年23期

基于深度学习的技能实体抽取研究
程煜¹,李济廷 ² ,韩明 ³
(1. 军委政治工作部军事人力资源保障中心,北京 100032;2. 军事科学院,北京 100071;3. 国防大学,北京 100091)

摘  要:在目前网络招聘成为主流招聘手段的背景下,产生了大量和求职者与岗位相关的数据,其中“技能”便是求职者和岗位之间的桥梁。文章围绕如何从繁多的招聘文本数据中抽取技能实体展开研究,将这一过程建模为命名实体识别任务,并基于深度学习的方法构建技能实体抽取模型。文章以 IT 领域为例,从网络招聘岗位描述文本中抽取技能实体,并对这些实体进行分析,为该领域的求职者提供了一定的参考和导向。


关键词:网络招聘;技能实体;深度学习;命名实体识别



DOI:10.19850/j.cnki.2096-4706.2022.23.029


基金项目:国家社会科学基金项目(2020-SKJJ-C-054)


中图分类号:TP399                                        文献标志码:A                                  文章编号:2095-2945(2022)23-0112-05


Research on Skill Entity Extraction Based on Deep Learning

CHENG Yu1, LI Jiting2, HAN Ming3

(1.Military Human Resources Support Center, Beijing 100032, China; 2.Chinese Academy of Military Science, Beijing 100071, China; 3.National Defense University, Beijing 100091, China)

Abstract: Under the background that online recruitment has become the mainstream recruitment method, a large number of data related to job seekers and positions have been generated, among which “skills” is the bridge between them. This paper focuses on how to extract skill entities from a wide range of recruitment text data to study, modeling this process as named entity recognition task, and building a skill entity extraction model based on deep learning method. Taking the IT field as an example, this paper extracts skill entities from the job description text of online recruitment, and analyzes these entities, which provides a certain reference and guidance for job seekers in this field.

Keywords: online recruitment; skill entity; deep learning; named entity recognition


参考文献:

[1] 王伟 . 就业市场对金融科技人才的需求——基于 2448 条招聘广告的文本分析 [J]. 财会月刊,2021(18):110-115.

[2] 孙瑜,莫凌飞 . 基于模糊匹配的招聘网页技能术语抽取研究 [J]. 信息技术与信息化,2018(11):171-177.

[3] 俞琰,陈磊,姜金德,等 . 网络招聘文本技能信息自动抽取研究 [J]. 图书情报工作,2019,63(13):105-113.

[4] PAN S J L,YANG Q.A Survey on Transfer Learning [J].IEEE Transactions on Knowledge and Data Engineering,2010,22(10):1345-1359.

[5] YADAV V,BETHARD S.A Survey on Recent Advances in Named Entity Recognition from Deep Learning Models [J/OL].arXiv: 1910.11470 [cs.CL].[2022-06-13].https://arxiv.org/abs/1910.11470.

[6] 李猛,李艳玲,林民 . 命名实体识别的迁移学习研究综述[J]. 计算机科学与探索,2021,15(2):206-218.

[7] EDDY S R.Hidden Markov Models [J].Current Opinion in Structurel Biology,1996,6(3):3612-3615.

[8] QUINLAN J R.Induction of Decision Trees [J].Machine Learning,1986,1(1):81-106.

[9] KAPUR J N.“book-Review” Maximum-Entropy Models in Science and Engineering [J].Biometrics,1992,48(1):333-334.

[10] CRISTIANINT N.An Introduction to Support Vector Machines and other Kernel-Based Learning Methods [M].Cambridge: Cambridge University Press,2000.

[11] LAFFERTY J D,MCCALLUM A,PEREIRA F C N.Conditional Random Fields:Probabilistic Models for Segmenting and Labeling Sequence Data [C]//Proceedings of the Eighteenth International Conference on Machine,2001:282-289.

[12] LI J,SUN A X,JOTY S.SEGBOT:A Generic Neural Text Segmentation Model with Pointer Network[C]//27th International Joint Conference on Artificial Intelligence.Stockholm:IJCAI,2018:4166-4172.

[13] 邓依依,邬昌兴,魏永丰,等 . 基于深度学习的命名实体识别综述 [J]. 中文信息学报,2021,35(9):30-45.

[14] LIANG D Y,XU W R,ZHAO Y G.Combining CharacterLevel Representation for Relation Classification [C]//26th International Conference on Artificial Neural Networks.Alghero:ICANN,2017:394-401.

[15] 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.

[16] SHEN Y Y,YUN H,LIPTON Z C,et al.Deep Active Learning for Named Entity Recognition [J/OL].arXiv:1707.05928 [cs. CL].[2022-06-16].https://arxiv.org/abs/1707.05928.

[17] HUANG Z H,XU W,YU K.Bidirectional LSTM-CRF Models for Sequence Tagging [J/OL].arXiv:1508.01991 [cs.CL].[2022- 06-17].https://arxiv.org/abs/1508.01991.[18] STRUBELL E,VERGA P,BELANGER D,et al.Fast and Accurate Entity Recognition with Iterated Dilated Convolutions [J/OL].arXiv:1702.02098 [cs.CL].[2022-06-18].https://arxiv.org/abs/1702.02098v3.


作者简介:程煜(1986—),男,汉族,山西长子人,工程师,硕士,研究方向:人力资源信息化;通讯作者:李济廷(1993—),男,满族,辽宁阜新人,助理研究员,博士,研究方向:系统优化与决策科学;韩明(1989—),男,汉族,黑龙江拜泉人,政治教导员,硕士,研究方向:政治工作信息化。