数字人文视域下面向历史古籍的信息抽取方法研究

doi:10.11959/j.issn.2096-0271.2022058

大数据 ›› 2022, Vol. 8 ›› Issue (6): 26-39.doi: 10.11959/j.issn.2096-0271.2022058

• 专题：面向人文领域的大数据技术和方法 • 上一篇下一篇

数字人文视域下面向历史古籍的信息抽取方法研究

韩立帆¹^,², 季紫荆¹^,², 陈子睿¹^,², 王鑫¹^,²

¹ 天津大学智能与计算学部，天津 300350
² 天津市认知计算与应用重点实验室，天津 300350

出版日期:2022-11-15 发布日期:2022-11-01
作者简介:韩立帆（1999- ）, 男, 天津大学智能与计算学部硕士生, 主要研究方向为自然语言处理、知识图谱构建
季紫荆（1997- ）, 女, 天津大学智能与计算学部硕士生, 主要研究方向为自然语言处理、知识图谱构建
陈子睿（1998- ）, 男, 天津大学智能与计算学部硕士生, 主要研究方向为知识表示学习、知识图谱问答、知识图谱构建
王鑫（1981- ），男，博士，天津大学智能与计算学部教授、博士生导师，主要研究方向为知识图谱数据管理、图数据库、大规模知识处理
基金资助:
科技创新2030—“新一代人工智能”重大项目(2020AAA0108504);国家自然科学基金资助项目(61972275)

Research on information extraction methods for historical classics under the threshold of digital humanities

Lifan HAN¹^,², Zijing JI¹^,², Zirui CHEN¹^,², Xin WANG¹^,²

¹ College of Intelligence and Computing, Tianjin University, Tianjin 300350, China
² Tianjin Key Laboratory of Cognitive Computing and Application, Tianjin 300350, China

Online:2022-11-15 Published:2022-11-01
Supported by:
Science and Technology Innovation 2030 “New Generation Artificial Intelligence” Major Project(2020AAA0108504);The National Natural Science Foundation of China(61972275)

摘要/Abstract

摘要：

数字人文旨在采用现代计算机网络技术助力传统人文研究，文言历史古籍是进行历史研究和学习的重要基础，但由于其写作语言为文言文，与现代所用的白话文在语法和词义上均有较大差别，因此不易于阅读和理解。针对上述问题，提出基于预训练模型对历史古籍中的实体和关系等进行知识抽取的方法，从而有效获取历史古籍文本中蕴含的丰富信息。该模型首先采用多级预训练任务代替BERT原有的预训练任务，以充分捕获语义信息，此外在BERT模型的基础上添加了卷积层及句子级聚合等结构，以进一步优化生成的词表示。然后，针对文言文标注数据稀缺的问题，构建了一个面向历史古籍文本标注任务的众包系统，获取高质量、大规模的实体和关系数据，完成文言文知识抽取数据集的构建，评估模型性能，并对模型进行微调。在构建的数据集及GulianNER数据集上的实验证明了提出模型的有效性。

关键词: 历史古籍, 预训练模型, 信息抽取, 众包机制

Abstract:

Digital humanities aims to use modern computer network technology to help traditional humanities research.Classical Chinese historical books are the important basis for historical research and learning, but since their writing language is classical Chinese, it is quite different from the vernacular Chinese in grammar and meaning, so it is not easy to read and understand.In view of the above problems, the solution to extract entities and relations in historical books based on pre-trained models was proposed to obtain the rich information contained in historical texts effectively.The model usedmulti-level pre-training tasks instead of BERT's original pre-training tasks to fully capture semantic information.And the model added some structures such as convolutional layers and sentence-level aggregations on the basis of the BERT model to optimize the generated word representation further.Then, in view of the scarcity of classical Chinese annotation data, a crowdsourcing system for the task of labeling historical classics was constructed, high-quality, large-scale entity and relation data was obtained and the classical Chinese knowledge extraction dataset was constructed.So it helped to evaluate the performance of the model and fine-tune the model.Experiments on the dataset constructed in this paper and on the GulianNER dataset demonstrated the effectiveness of the model proposed in this paper.

Key words: historical classics, pre-trained model, information extraction, crowdsourcing mechanism

中图分类号:

TP391.1

韩立帆, 季紫荆, 陈子睿, 王鑫. 数字人文视域下面向历史古籍的信息抽取方法研究[J]. 大数据, 2022, 8(6): 26-39.

Lifan HAN, Zijing JI, Zirui CHEN, Xin WANG. Research on information extraction methods for historical classics under the threshold of digital humanities[J]. Big Data Research, 2022, 8(6): 26-39.

图/表 9

图1

图2

图3

表1

表2

表3

图4

图5

图6

参考文献 24

[1]	DEVLIN J , CHANG M , LEE K ,et al. BERT:pre-training of deep bidirectional transformers for language understanding[C]// Proceedings of NAACLHLT.[S.l.:s.n.], 2019: 4171-4186.
[2]	HOWE J . The rise of crowdsourcing[J]. Wired, 2006,14(6): 176-183.
[3]	HOLLEY R . Crowdsourcing:how and why should libraries do it?[J]. D-Lib Magazine, 2010,16(3/4): 1-21.
[4]	OOMEN J , AROYO L . Crowdsourcing in the cultural heritage domain:opportunities and challenges[C]// Proceedings of the 5th International Conference on Communities and Technologies.[S.l.:s.n.], 2011: 138-149.
[5]	TERRAS M . Digital curiosities:resource creation via amateur digitization[J]. Literary and Linguistic Computing, 2010,25(4): 425-438.
[6]	RIDGE M , . Citizen history and its discontents[C]// Proceedings of 2014 IHR Digital History Seminar.[S.l.:s.n.], 2014: 1-13.
[7]	ZHANG X H , SONG S J , ZHAO Y C ,et al. Motivations of volunteers in the Transcribe Sheng project:a grounded theory approach[J]. Proceedings of the Association for Information Science and Technology, 2018,55(1): 951-953.
[8]	RIDGE M . From tagging to theorizing:deepening engagement with cultural heritage through crowdsourcing[J]. Curator:the Museum Journal, 2013,56(4): 435-450.
[9]	DANIELS C , HOLTZE T L , HOWARD R I ,et al. Community as resource:crowdsourcing transcription of an historic newspaper[J]. Journal of Electronic Resources Librarianship, 2014,26(1): 36-48.
[10]	CONCILIO G , VITELLIO I . Cocreating intangible cultural heritage by crowd-mapping: the case of mappi[na][C]// Proceedings of 2016 IEEE 2nd International Forum on Research and Technologies for Society and Industry Leveraging a Better Tomorrow. Piscataway:IEEE Press, 2016: 1-5.
[11]	RUMELHART D E , HINTON G E , WILLIAMS R J . Learning representations by back-propagating errors[J]. Nature, 1986,323(6088): 533-536.
[12]	HINTON G E , MCCLELLAND J L , RUMELHART D E . Distributed representations[M]. Cambridge: MIT Press, 1986: 77-109.
[13]	MIKOLOV T , CHEN K , CORRADO G ,et al. Efficient estimation of word representations in vector space[J]. arXiv preprint,2013,arXiv:1301.3781.
[14]	MCCANN B , BRADBURY J , XIONG C ,et al. Learned in translation:contextualized word vectors[C]// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook:Curran Associates Inc, 2017: 6297-6308.
[15]	PETERS M , NEUMANN M , IYYER M ,et al. Deep contextualized word representations[C]// Proceedings of 2018 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies,Volume 1 (Long Papers). Stroudsburg:Association for Computational Linguistics, 2018: 2227-2237.
[16]	VASWANI A , SHAZEER N , PARMAR N ,et al. Attention is all you need[J]. Advances in Neural Information Processing Systems, 2017,30.
[17]	STAUDEMEYER R C , MORRIS E R . Understanding LSTM-a tutorial into long short-term memory recurrent neural networks[J]. arXiv preprint,2019,arXiv:1909.09586.
[18]	RADFORD A , NARASIMHAN K , SALIMANS T ,et al. Imporoving language understanding by generative pretraining[Z]. 2018.
[19]	MA X Z , HOVY E . End-to-end sequence labeling via Bi-directional LSTMCNNs-CRF[C]// Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1:Long Papers). Stroudsburg:Association for Computational Linguistics, 2016.
[20]	LIU Y , OTT M , GOYAL N ,et al. RoBERta:a robustly optimized bert pretraining approach[J]. arXiv preprint,2019,arXiv:1907.11692.
[21]	LAN Z , CHEN M , GOODMAN S ,et al. Albert:a lite bert for self-supervised learning of language representations[J]. arXiv preprint,2019,arXiv:1909.11942.
[22]	YANG Z , DAI Z , YANG Y ,et al. Xlnet:generalized autoregressive pretraining for language understanding[C]// Proceedings of the 33rd International Conference on Neural Information Processing Systems. Red Hook:Curran Associates Inc, 2019: 5753-5763.
[23]	CUI Y M , CHE W X , LIU T ,et al. Pretraining with whole word masking for Chinese BERT[J]. IEEE/ACM Transactions on Audio,Speech,and Language Processing, 2021,29: 3504-3514.
[24]	王东波, 刘畅, 朱子赫 ,等. SikuBERT与SikuRoBERTa：面向数字人文的《四库全书》预训练模型构建及应用研究[J]. 图书馆论坛, 2022,42(6): 31-43.
	WANG D B , LIU C , ZHU Z H ,et al. Construction and application of pretrained models of Siku Quanshu in orientation to digital humanities[J]. Library Tribune, 2022,42(6): 31-43.

实体类型	训练集/个	校验集/个	测试集/个	总数/个
人名	9 467	1 267	701	11 435
地名	2 962	391	167	3 520
职位名	1 750	242	139	2 131
组织名	1 698	266	100	2 064
其他	110	18	9	137

关系类型	训练集/个	校验集/个测试集/个	总数/个
人名-人名	1 139	324130	1 593
人名-地名	462	129 53	644
人名-职位名	1 093	319162	1 574
人名-组织名	231	6038	329
其他	157	4028	225

实体类型	训练集/个	校验集/个	测试集/个	总数/个
书名	27 445	11 531	5 633	44 609
其他专名	91 917	20 972	5 552	118 441

数字人文视域下面向历史古籍的信息抽取方法研究

Research on information extraction methods for historical classics under the threshold of digital humanities

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 24

相关文章 1

Metrics

推荐阅读 0