Journal of Scientific Information Research
Keywords
allusion identification; decision-layer fusion; sequence labeling; large language model; prompt learning
Abstract
[Purpose/significance]Allusions, as an important and widely used rhetorical device in literary creation, hold immeasurable value for the study of ancient Chinese literature. Despite this, the automatic identification technology for allusions is not yet mature and currently relies mainly on manual identification, which requires further in-depth research. [Method/process]The article proposes an allusion citation recognition method that incorporates the function of making corrections using large language models at the decision-making level. This method combines traditional sequence labeling techniques with general large language models, introduces prompt templates, and performs output fu‐ sion at the decision layer to improve accuracy. In addition, this study also constructs a set of evaluation metrics specifically for the problem of allusion identification. [Result/conclusion]Through generalization testing, the AR_BBC_LP allusion identification model performed excellently in the experiment, with P_allu, R_allu, and F1_allu reaching 89.75%, 89.38%, and 89.56% respectively, significantly better than existing baseline models. The results show that the model not only enhances the performance of traditional sequence labeling models but also opens up new areas for the application of large language models. It also provides a new perspective and strong methodological support for the identification of allusions and their application in the study of ancient Chinese literature.
First Page
37
Last Page
52
Submission Date
16-May-2024
Revision Date
17-Jul-2024
Acceptance Date
18-Jul-2024
Published Date
01-Oct-2024
Reference
[1] 程羽黑.古典诗歌用典论[J].复旦学报(社会科学版),2023,65(05):80-88.
[2] 谌东飚.唐前诗歌用典考察[J].长沙水电师院社会科学学报,1996(04):57-62.
[3] 李娅琳,李佳静.援诗艺入集句诗:王安石集句诗写作略论[J].今古文创,2023(12):49-51.
[4] 吴承学.论宋代櫽括词[J].文学遗产,2000(04):74-83,143.
[5] 范进军.试论稼轩词用典的方式[J].船山学刊,2006(01):111-114.
[6] 罗嗣亮,江秋飞.“第二个结合”:出场逻辑、结合理路和实践原则:以毛泽东妙用中国神话典故为例[J].毛泽东研究,2023(04):84-94.
[7] 刘鹤亭.从习近平用典看“两个结合”:以对《庄子》的引用为例[J].邓小平研究,2023(05):51-63.
[8] 张辉.谈古诗词的用典[J].襄樊职业技术学院学报,2003(03):67-70.
[9] 范之麟.全宋词典故辞典[M].武汉:湖北辞书出版社,2001.
[10] 王东波,高瑞卿,沈思,等.面向先秦典籍的历史事件基本实体构件自动识别研究[J].国家图书馆学刊,2018,27(01):65-77.
[11] 刘江峰,冯钰童,王东波,等.数字人文视域下SikuBERT增强的史籍实体识别[J].图书馆论坛,2022(10):1-14.
[12] 崔竞烽,郑德俊,王东波,等.基于深度学习模型的菊花古典诗词命名实体识别[J].情报理论与实践,2020,43(11):150-155.
[13] 谢靖,刘江峰,王东波.古代中国医学文献的命名实体识别研究:以Flat-lattice增强的SikuBERT预训练模型为例[J].图书馆论坛,2022,42(10):51-60.
[14] TAY Y,DEHGHANI M,BAHRI D,et al.Efficient transformers:A survey[J].ACM Computing Surveys, 2022,55(06):109.
[15] BROWN T B,MANN B,RYDER N,et al.Language model sare few-shot learners[C]//Proceeding softhe 34th International Conferenceon Neural Information Processing Systems.Vancouver,Canada:ACM,2020:1877-1901.
[16] 李南,丁益东,江浩宇,等.面向大语言模型的越狱攻击综述[J].计算机研究与发展,2024,61(05):1156-1181.
[17] 马草.诗性功能与文学自觉:魏晋南北朝文学用典的审美原理考察[J].哈尔滨工业大学学报(社会科学版),2018,20(06):75-81.
[18] 秦红丽.晚唐诗歌用典艺术研究[D].南京:南京师范大学,2019.
[19] 郑开元.阮籍典故的形成及其在唐诗中的“二次赋义”[J].湖南工程学院学报(社会科学版),2023,33(03):80-87.
[20] 方贝儿.辛弃疾“宗庄”论析:基于稼轩词涉《庄》典故统计的考察[J].今古文创,2023(28):50-54.
[21] 王芊.论陆游诗歌中的马意象[J].汉字文化,2023(16):131-133.
[22] 王天天,陈洪.论陶诗之议论:以“饮酒”诗为例[J].甘肃开放大学学报,2023,33(04):37-43.
[23] 周莉娜.面向领域知识服务的唐诗本体构建与智能应用研究[D].武汉:武汉大学,2020.
[24] 宋雪雁,罗慧,裴心源,等.知识重组视域下《全唐诗》送别诗的典故运用及文化意象研究[J].图书情报工作,2023,67(20):25-33.
[25] TANG X,LIANG S,ZHENG J,et al.Automatic Recognition of Allusions in Tang Poetry Based on BERT [C]//2019 International Conference on Asian Language Processing(IALP),2019:255-260.
[26] LIU L,CHEN X,HE B.End-to-End Multi-task Learning for Allusion Detection in Ancient Chinese Poems[J].Knowledge Science,Engineering and Management(KSEM),2020:300-311.
[27] 范涛,王昊,林克柔,等.基于视觉的网络舆情事件中网民情感分析研究[J].情报资料工作,2022,43(04):83-91.
[28] 李静茹.唐诗用典《世说新语》研究[D].重庆:重庆工商大学,2020.
[29] 王砚文.汉语同源异形典故词语的界定、类型与形成机制[J].现代语文,2021(12):33-38.
[30] DEVLIN J,CHANG M W,LEE K,et al.BERT:Pre-Training of Deep Bidirectional Transformers for Language Understanding[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies,Volume 1(Long and Short Papers).Stroudsburg,PA:Association for Computational Linguistics,2019:4171-4186.
[31] 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(06):31-43.
[32] HOCHREITER S,SCHMIDHUBER J.Long Short-Term Memory[J].Neural Computation,1997,9(08):1735-1780.
[33] DU Z,QIAN Y,LIU X,et al.GLM:General language model pretraining with autoregressive blank infilling[C]//Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics(Volume 1:Long Papers).Dublin:ACL,2022:320-335.
[34] TOUVRON H,LAVRIL T,IZACARD G,et al.LLaMA:Open and Efficient Foundation Language Models[J].arXiv preprint arXiv:2302.13971,2023.
[35] 曾慧玲,李琳,吕思洋,等.提示学习驱动的新闻舆情风险识别方法研究[J].计算机工程与应用,2022,60(01):182-188.
[36] 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,2023,55(09):1-35.
[37] 史锡尧.诗句掩盖下的句法结构:古典诗词的诗句与一般句子的异同[J].修辞学习,2002(06):33-34.
Digital Object Identifier (DOI)
10.19809/j.cnki.kjqbyj.2024.04.004
Recommended Citation
BU, Wenru; WANG, Hao; LI, Xiaomin; ZHOU, Shu; and DENG, Sanhong
(2024)
"The Exploration of Ancient Poetry: A Decision-Level Fusion of Large Model Corrections for Allusion Citation Recognition Methods,"
Journal of Scientific Information Research: Vol. 6:
Iss.
4, Article 4.
DOI: 10.19809/j.cnki.kjqbyj.2024.04.004
Available at:
https://eng.kjqbyj.com/journal/vol6/iss4/4