The Exploration of Ancient Poetry: A Decision-Level Fusion of Large Model Corrections for Allusion Citation Recognition Methods

Authors

Wenru BU, 1.School of Information Management, Nanjing University, Nanjing 210023 2.Key Laboratory of Data Engineering and Knowledge Services in Provincial Universities （Nanjing University）, Nanjing 210023
Hao WANG, 1.School of Information Management, Nanjing University, Nanjing 210023 2.Key Laboratory of Data Engineering and Knowledge Services in Provincial Universities （Nanjing University）, Nanjing 210023
Xiaomin LI, 1.School of Information Management, Nanjing University, Nanjing 210023 2.Key Laboratory of Data Engineering and Knowledge Services in Provincial Universities （Nanjing University）, Nanjing 210023
Shu ZHOU, 1.School of Information Management, Nanjing University, Nanjing 210023 2.Key Laboratory of Data Engineering and Knowledge Services in Provincial Universities （Nanjing University）, Nanjing 210023
Sanhong DENG, 1.School of Information Management, Nanjing University, Nanjing 210023 2.Key Laboratory of Data Engineering and Knowledge Services in Provincial Universities （Nanjing University）, Nanjing 210023

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

May 2024

Revision Date

July 2024

Acceptance Date

July 2024

Publication Date

October 2024

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," 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