Journal of Computer Applications ›› 2024, Vol. 44 ›› Issue (12): 3815-3822.DOI: 10.11772/j.issn.1001-9081.2023121719
• Artificial intelligence • Previous Articles Next Articles
Yingjie GAO1, Min LIN1(), Siriguleng2,3, Bin LI1, Shujun ZHANG1,2
Received:
2023-12-15
Revised:
2024-02-15
Accepted:
2024-02-26
Online:
2024-03-11
Published:
2024-12-10
Contact:
Min LIN
About author:
GAO Yingjie, born in 1999, M. S. candidate. Her research interests include natural language processing.Supported by:
高颖杰1, 林民1(), 斯日古楞null2,3, 李斌1, 张树钧1,2
通讯作者:
林民
作者简介:
高颖杰(1999—),女,内蒙古锡林郭勒人,硕士研究生,主要研究方向:自然语言处理基金资助:
CLC Number:
Yingjie GAO, Min LIN, Siriguleng, Bin LI, Shujun ZHANG. Prompt learning method for ancient text sentence segmentation and punctuation based on span-extracted prototypical network[J]. Journal of Computer Applications, 2024, 44(12): 3815-3822.
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.
Add to citation manager EndNote|Ris|BibTeX
URL: https://www.joca.cn/EN/10.11772/j.issn.1001-9081.2023121719
方法 | 数据集规模 (字数)/107 | Pre/% | Rec/% | F1/% |
---|---|---|---|---|
BERT-BiGRU-CRF[ | 0.421 | 80.00 | 63.43 | 70.76 |
BERT-FLAT-CRF[ | 0.900 | 87.11 | 74.95 | 80.57 |
Siku-BERT[ | 2.600 | 87.86 | 87.92 | 87.86 |
BERT+微调[ | 2.900 | 70.92 | 69.88 | 70.40 |
BERT-LSTM-CRF[ | 10.200 | — | — | 90.84 |
SpanProtoNet | 0.038 | 88.94 | 88.96 | 88.95 |
Tab. 1 Analysis of dataset size and indicators for different methods
方法 | 数据集规模 (字数)/107 | Pre/% | Rec/% | F1/% |
---|---|---|---|---|
BERT-BiGRU-CRF[ | 0.421 | 80.00 | 63.43 | 70.76 |
BERT-FLAT-CRF[ | 0.900 | 87.11 | 74.95 | 80.57 |
Siku-BERT[ | 2.600 | 87.86 | 87.92 | 87.86 |
BERT+微调[ | 2.900 | 70.92 | 69.88 | 70.40 |
BERT-LSTM-CRF[ | 10.200 | — | — | 90.84 |
SpanProtoNet | 0.038 | 88.94 | 88.96 | 88.95 |
方法 | Pre | Rec | F1 |
---|---|---|---|
ERNIE3.0 | 67.83 | 64.16 | 64.72 |
Siku-BERT | 84.01 | 84.71 | 84.36 |
Siku-RoBERTa | 84.22 | 84.85 | 84.53 |
Siku-BERT-BiLSTM-CRF | 86.14 | 85.22 | 85.65 |
Siku-BERT-BiGRU-CRF | 86.46 | 86.52 | 86.48 |
Xunzi-QWen-Chat | 88.92 | 96.43 | 92.52 |
SpanProtoNet | 88.94 | 88.96 | 88.95 |
Tab. 2 Experimental results on Records of the Grand Historian dataset
方法 | Pre | Rec | F1 |
---|---|---|---|
ERNIE3.0 | 67.83 | 64.16 | 64.72 |
Siku-BERT | 84.01 | 84.71 | 84.36 |
Siku-RoBERTa | 84.22 | 84.85 | 84.53 |
Siku-BERT-BiLSTM-CRF | 86.14 | 85.22 | 85.65 |
Siku-BERT-BiGRU-CRF | 86.46 | 86.52 | 86.48 |
Xunzi-QWen-Chat | 88.92 | 96.43 | 92.52 |
SpanProtoNet | 88.94 | 88.96 | 88.95 |
模型结构 | Pre | Rec | F1 |
---|---|---|---|
Siku-BERT | 84.01 | 84.71 | 84.36 |
Siku-BERT-Span-Linear | 85.86 | 87.24 | 86.54 |
SpanProtoNet | 88.94 | 88.96 | 88.95 |
Tab. 3 Results of ablation experiment
模型结构 | Pre | Rec | F1 |
---|---|---|---|
Siku-BERT | 84.01 | 84.71 | 84.36 |
Siku-BERT-Span-Linear | 85.86 | 87.24 | 86.54 |
SpanProtoNet | 88.94 | 88.96 | 88.95 |
方法 | Pre | Rec | F1 |
---|---|---|---|
ERNIE3.0 | 70.02 | 70.11 | 70.06 |
Siku-BERT | 87.86 | 87.92 | 87.86 |
Siku-BERT-BiLSTM-CRF | 91.77 | 91.84 | 91.80 |
Siku-BERT-BiGRU-CRF | 92.63 | 92.43 | 92.52 |
Xunzi-QWen-Chat | 91.35 | 96.77 | 93.98 |
SpanProtoNet | 91.60 | 94.68 | 93.12 |
Tab. 4 Experimental results on CCLUE dataset
方法 | Pre | Rec | F1 |
---|---|---|---|
ERNIE3.0 | 70.02 | 70.11 | 70.06 |
Siku-BERT | 87.86 | 87.92 | 87.86 |
Siku-BERT-BiLSTM-CRF | 91.77 | 91.84 | 91.80 |
Siku-BERT-BiGRU-CRF | 92.63 | 92.43 | 92.52 |
Xunzi-QWen-Chat | 91.35 | 96.77 | 93.98 |
SpanProtoNet | 91.60 | 94.68 | 93.12 |
预训练模型 | Pre | Rec | F1 |
---|---|---|---|
Siku-BERT | 99.51 | 99.21 | 99.36 |
Siku-RoBERT | 99.38 | 99.69 | 99.53 |
Tab. 5 Experimental results of position extractors
预训练模型 | Pre | Rec | F1 |
---|---|---|---|
Siku-BERT | 99.51 | 99.21 | 99.36 |
Siku-RoBERT | 99.38 | 99.69 | 99.53 |
原文内容 | 预测内容 | F1 | |
---|---|---|---|
位置 预测 | 类别 预测 | ||
杓端有两星:一内为矛, 招摇;一外为盾,天锋。 有句圜十五星,属杓, 曰贱人之牢。其牢中星 实则囚多,虚则开出。 天一、枪、棓、矛、盾动摇, 角大,兵起。 | 杓端有两星:一内为矛,招摇;一外为盾,天锋。有句圜十五星,属杓, 曰贱人之牢;其牢中星实则囚多,虚则开出。天一、枪、棓、矛,盾, 动摇,角大,兵起。 | 96.90 | 85.43 |
黄帝者,少典之子, 姓公孙,名曰轩辕。 生而神灵,弱而能言, 幼而徇齐,长而敦敏, 成而聪明。轩辕之时, 神农氏世衰。 诸侯相侵伐,暴虐百姓, 而神农氏弗能征。 | 黄帝者,少典之子, 姓公孙,名曰轩辕。 生而神灵,弱而能言, 幼而徇齐,长而敦敏, 成而聪明;轩辕之时, 神农氏世衰。 诸侯相侵伐,暴虐百姓,而神农氏弗能征。 | 100.00 | 92.86 |
Tab. 6 Error case analysis
原文内容 | 预测内容 | F1 | |
---|---|---|---|
位置 预测 | 类别 预测 | ||
杓端有两星:一内为矛, 招摇;一外为盾,天锋。 有句圜十五星,属杓, 曰贱人之牢。其牢中星 实则囚多,虚则开出。 天一、枪、棓、矛、盾动摇, 角大,兵起。 | 杓端有两星:一内为矛,招摇;一外为盾,天锋。有句圜十五星,属杓, 曰贱人之牢;其牢中星实则囚多,虚则开出。天一、枪、棓、矛,盾, 动摇,角大,兵起。 | 96.90 | 85.43 |
黄帝者,少典之子, 姓公孙,名曰轩辕。 生而神灵,弱而能言, 幼而徇齐,长而敦敏, 成而聪明。轩辕之时, 神农氏世衰。 诸侯相侵伐,暴虐百姓, 而神农氏弗能征。 | 黄帝者,少典之子, 姓公孙,名曰轩辕。 生而神灵,弱而能言, 幼而徇齐,长而敦敏, 成而聪明;轩辕之时, 神农氏世衰。 诸侯相侵伐,暴虐百姓,而神农氏弗能征。 | 100.00 | 92.86 |
1 | 王丽丽,张宁. 数字人文视角下的古籍知识关联探析[J]. 农业图书情报学报, 2022, 34(9):51-59. |
WANG L L, ZHANG N. Knowledge correlation of Chinese ancient books from the perspective of digital humanity[J]. Journal of Library and Information Science in Agriculture, 2022, 34(9): 51-59. | |
2 | 王博立,史晓东,苏劲松.一种基于循环神经网络的古文断句方法[J]. 北京大学学报(自然科学版), 2017, 53(2):255-261. |
WANG B L, SHI X D, SU J S. A sentence segmentation method for ancient Chinese texts based on recurrent neural network[J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2017, 53(2): 255-261. | |
3 | HAN X, WANG H, ZHANG S, et al. Sentence segmentation for classical Chinese based on LSTM with radical embedding [J]. The Journal of China Universities of Posts and Telecommunications, 2019, 26(2): 1-8. |
4 | VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need [C]// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2017: 6000-6010. |
5 | 俞敬松,魏一,张永伟. 基于BERT的古文断句研究与应用[J]. 中文信息学报, 2019, 33(11):57-63. |
YU J S, WEI Y, ZHANG Y W. Automatic ancient Chinese texts segmentation based on BERT[J]. Journal of Chinese Information Processing, 2019, 33(11):57-63. | |
6 | 洪涛,程瑞雪,刘思汐,等. 一种基于Transformer模型的古籍自动标点技术[J]. 数字人文, 2021(2): 111-122. |
HONG T, CHENG R X, LIU S X, et al. An automatic punctuation technique based on Transformer model [J]. Digital Humanities, 2021(2):111-122. | |
7 | 王倩,王东波,李斌,等. 面向海量典籍文本的深度学习自动断句与标点平台构建研究[J]. 数据分析与知识发现, 2021, 5(3):25-34. |
WANG Q, WANG D B, LI B, et al. Deep learning based automatic sentence segmentation and punctuation model for massive classical Chinese literature[J]. Data Analysis and Knowledge Discovery, 2021, 5(3): 25-34. | |
8 | 陈天莹,陈蓉,潘璐璐,等. 基于前后文n-gram模型的古汉语句子切分[J]. 计算机工程, 2007, 33(3):192-193, 196. |
CHEN T Y, CHEN R, PAN L L, et al. Archaic Chinese punctuating sentences based on context n-gram model[J]. Computer Engineering, 2007, 33(3):192-193, 196. | |
9 | 黄建年,侯汉清. 农业古籍断句标点模式研究[J]. 中文信息学报, 2008, 22(4):31-38. |
HUANG J N, HOU H Q. On sentence segmentation and punctuation model for ancient books on agriculture[J]. Journal of Chinese Information Processing, 2008, 22(4):31-38. | |
10 | 张开旭,夏云庆,宇航. 基于条件随机场的古汉语自动断句与标点方法[J]. 清华大学学报(自然科学版), 2009, 49(10):1733-1736. |
ZHANG K X, XIA Y Q, YU H. CRF-based approach to sentence segmentation and punctuation for ancient Chinese prose [J]. Journal of Tsinghua University (Science and Technology), 2009, 49(10): 1733-1736. | |
11 | WANG B, SHI X, TAN Z, et al. A sentence segmentation method for ancient Chinese texts based on NNLM [C]// Proceedings of the 2016 Workshop on Chinese Lexical Semantics. Cham: Springer, 2016: 387-396. |
12 | 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 pre-trained models of Siku Quanshu in orientation to digital humanities [J]. Library Tribune, 2022, 42(6):31-43. | |
13 | 赵连振,张逸勤,刘江峰,等. 面向数字人文的先秦两汉典籍自动标点研究——以SikuBERT预训练模型为例[J]. 图书馆论坛, 2022, 42(12):120-128, 137. |
ZHAO L Z, ZHANG Y Q, LIU J F, et al. Study on automatic punctuation of ancient Chinese classics of pre-Qin and Han dynasties in the context of digital humanities: taking SikuBERT pre-training model for example [J]. Library Tribune, 2022, 42(12): 120-128, 137. | |
14 | 王瑶,顾磊. 基于BERT+BiLSTM+CRF模型与新预处理方法的古籍自动标点[J]. 软件导刊, 2022, 21(9):7-13. |
WANG Y, GU L. Automatic punctuation of ancient books based on BERT+BiLSTM+CRF model and new preprocessing method [J]. Software Guide, 2022, 21(9):7-13. | |
15 | 程宁. 基于深度学习的古籍文本断句与词法分析一体化处理技术研究[D]. 南京:南京师范大学, 2020:53-57. |
CHENG N. Research on integrated processing technology of sentence segmentation and lexical analysis of ancient books based on deep learning [D]. Nanjing: Nanjing Normal University, 2020:53-57. | |
16 | 庄百川. 基于深度学习的古文自动断句与标点研究[D]. 武汉:武汉邮电科学研究院, 2022:41-50. |
ZHUANG B C. Automatic segmentation and punctuation of ancient Chinese based on deep learning [D]. Wuhan: Wuhan Research Institute of Posts and Telecommunications, 2022:41-50. | |
17 | 韩旭. 基于Transformer-CRF的文言文断句方法研究——以唐代墓志铭为例[J]. 情报工程, 2021, 7(5):30-39. |
HAN X. Research on sentence segmentation of classical Chinese based on Transformer-CRF: taking epitaph of Tang dynasty as an example[J]. Technology Intelligence Engineering, 2021, 7(5):30-39. | |
18 | WANG Y, YAO Q, KWOK J T, et al. Generalizing from a few examples: a survey on few-shot learning[J]. ACM Computing Surveys, 2021, 53(3): No.63. |
19 | HUISMAN M, VAN RIJN J N, PLAAT A. A survey of deep meta-learning [J]. Artificial Intelligence Review, 2021, 54: 4483-4541. |
20 | KULKARNI V, MEHDAD Y, CHEVALIER T. Domain adaptation for named entity recognition in online media with word embeddings[EB/OL]. [2023-12-12].. |
21 | SNELL J, SWERSKY K, ZEMEL R. Prototypical networks for few-shot learning[C]// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook: Curran Associates Inc., 2017: 4080-4090. |
22 | WEI J, ZOU K. EDA: easy data augmentation techniques for boosting performance on text classification tasks [C]// Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Stroudsburg: ACL, 2019:6382-6388. |
23 | GENG R, LI B, LI Y, et al. Dynamic memory induction networks for few-shot text classification [C]// Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg: ACL, 2020: 1087-1094. |
24 | SHENG J, GUO S, CHEN Z, et al. Adaptive attentional network for few-shot knowledge graph completion [C]// Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: ACL, 2020: 1681-1691. |
25 | WANG J, WANG C, TAN C, et al. SpanProto: a two-stage span-based prototypical network for few-shot named entity recognition [C]// Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: ACL, 2022: 3466-3476. |
26 | YUAN Z, CHEN Z, ZHOU Y, et al. Enhance prototypical network with hybrid loss for few-shot text classification [J]. Journal of Physics: Conference Series, 2023, 2555: No.012017. |
27 | FANG Y, LIU Z, PAN S, et al. Few-shot relation extraction based on multi-level feature metric learning [C]// Proceedings of the SPIE 12610, 3rd International Conference on Artificial Intelligence and Computer Engineering. Bellingham, WA: SPIE, 2022: No.1261058. |
28 | KAUFMANN B, BUSBY D, DAS C K, et al. Validation of a zero-shot learning natural language processing tool for data abstraction from unstructured healthcare data [EB/OL]. [2023-12-08].. |
29 | 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, 2020, 55(9): No.195. |
30 | 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. |
31 | LI X L, LIANG P. Prefix-tuning: optimizing continuous prompts for generation [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: 4582-4597. |
32 | LIU X, ZHENG Y, DU Z, et al. GPT understands, too [EB/OL]. [2023-12-09].. |
33 | SUN Y, WANG S, FENG S, et al. ERNIE 3.0: large-scale knowledge enhanced pre-training for language understanding and generation[EB/OL]. [2023-12-12].. |
[1] | Shunyong LI, Shiyi LI, Rui XU, Xingwang ZHAO. Incomplete multi-view clustering algorithm based on self-attention fusion [J]. Journal of Computer Applications, 2024, 44(9): 2696-2703. |
[2] | Yunchuan HUANG, Yongquan JIANG, Juntao HUANG, Yan YANG. Molecular toxicity prediction based on meta graph isomorphism network [J]. Journal of Computer Applications, 2024, 44(9): 2964-2969. |
[3] | Yexin PAN, Zhe YANG. Optimization model for small object detection based on multi-level feature bidirectional fusion [J]. Journal of Computer Applications, 2024, 44(9): 2871-2877. |
[4] | Jing QIN, Zhiguang QIN, Fali LI, Yueheng PENG. Diagnosis of major depressive disorder based on probabilistic sparse self-attention neural network [J]. Journal of Computer Applications, 2024, 44(9): 2970-2974. |
[5] | Xiyuan WANG, Zhancheng ZHANG, Shaokang XU, Baocheng ZHANG, Xiaoqing LUO, Fuyuan HU. Unsupervised cross-domain transfer network for 3D/2D registration in surgical navigation [J]. Journal of Computer Applications, 2024, 44(9): 2911-2918. |
[6] | Yuhan LIU, Genlin JI, Hongping ZHANG. Video pedestrian anomaly detection method based on skeleton graph and mixed attention [J]. Journal of Computer Applications, 2024, 44(8): 2551-2557. |
[7] | Yanjie GU, Yingjun ZHANG, Xiaoqian LIU, Wei ZHOU, Wei SUN. Traffic flow forecasting via spatial-temporal multi-graph fusion [J]. Journal of Computer Applications, 2024, 44(8): 2618-2625. |
[8] | Qianhong SHI, Yan YANG, Yongquan JIANG, Xiaocao OUYANG, Wubo FAN, Qiang CHEN, Tao JIANG, Yuan LI. Multi-granularity abrupt change fitting network for air quality prediction [J]. Journal of Computer Applications, 2024, 44(8): 2643-2650. |
[9] | Yiqun ZHAO, Zhiyu ZHANG, Xue DONG. Anisotropic travel time computation method based on dense residual connection physical information neural networks [J]. Journal of Computer Applications, 2024, 44(7): 2310-2318. |
[10] | Song XU, Wenbo ZHANG, Yifan WANG. Lightweight video salient object detection network based on spatiotemporal information [J]. Journal of Computer Applications, 2024, 44(7): 2192-2199. |
[11] | Xindong YOU, Yingzi WEN, Xinpeng SHE, Xueqiang LYU. Triplet extraction method for mine electromechanical equipment field [J]. Journal of Computer Applications, 2024, 44(7): 2026-2033. |
[12] | Xun SUN, Ruifeng FENG, Yanru CHEN. Monocular 3D object detection method integrating depth and instance segmentation [J]. Journal of Computer Applications, 2024, 44(7): 2208-2215. |
[13] | Zheng WU, Zhiyou CHENG, Zhentian WANG, Chuanjian WANG, Sheng WANG, Hui XU. Deep learning-based classification of head movement amplitude during patient anaesthesia resuscitation [J]. Journal of Computer Applications, 2024, 44(7): 2258-2263. |
[14] | Huanhuan LI, Tianqiang HUANG, Xuemei DING, Haifeng LUO, Liqing HUANG. Public traffic demand prediction based on multi-scale spatial-temporal graph convolutional network [J]. Journal of Computer Applications, 2024, 44(7): 2065-2072. |
[15] | Zhi ZHANG, Xin LI, Naifu YE, Kaixi HU. DKP: defending against model stealing attacks based on dark knowledge protection [J]. Journal of Computer Applications, 2024, 44(7): 2080-2086. |
Viewed | ||||||
Full text |
|
|||||
Abstract |
|
|||||