基於深度學習方法之佛教引用句推薦系統

A Buddhist Quote Recommendation System Based on Deep Learning Approaches

釋廣慧(Guanghui Shi) ； 王昱鈞(Yu-Chun Wang) ； 洪振洲(Jen-Jou Hung)

《數位典藏與數位人文》 11期 (2023/04) Pp. 105-133

https://doi.org/10.6853/DADH.202304_(11).0004

摘要

在寫作之中，適度引用名言佳句是常用之撰寫技巧，能增進文章說服力，讓文章更加優美令人信服。而佛教典籍之中有非常多深具哲理與啟發之名句，許多創作之中亦時常引用佛教經典之語句以闡述其文之要旨，然對於現代人來說，要在寫作時引用佛教相關之引用句實非易事。因此能於文章寫作時依據當前內容自動推薦合適的佛教引用句即為一重要的需求與研究課題，本論文即針對佛教引用句推薦問題，提出基於長短期記憶（Long Short-Term Memory, LSTM）與基於轉換器的雙向編碼器表徵技術（Bidirectional Encoder Representations from Transformers, BERT）兩種深度學習方法之佛教引用句推薦系統，可自動從文章內容進行分析推薦合適的佛教引用句。我們建置佛教引用句資料集，藉以訓練深度學習模型，實驗結果顯示系統之推薦準確率可高達0.9148，其能有效進行寫作時之佛教引用句推薦。

關鍵字

佛教引用句 ； 推薦系統 ； 深度學習 ； 長短期記憶 ； BERT

並列摘要

In writing, citing famous sayings is a common writing technique, which can enhance the persuasiveness of the article and make the article more convincing. Buddhist quotes are one the vital sources of maxims. These Buddhist quotes are full of wisdom and often enlighten people. However, for modern people, knowing how to cite a suitable inspiring Buddhist quote are not an easy job. Therefore, a recommendation system which is able to automatically recommend suitable Buddhist quotes according to the content while writing becomes an urgent demand. This paper proposes a Buddhist quote recommendation system based on two deep learning approaches, such as LSTM and BERT. We compile a data set for Buddhist quote recommendations and then train a deep learning model. The experimental results show that the accuracy of our system achieves 0.9148, which demonstrates our system effectively recommends suitable Buddhist quotes when writing.

並列關鍵字

Buddhist quotes ； recommendation system ； deep learning ； LSTM ； BERT

參考文獻

Cho, K., Van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning phrase representations using RNN encoder-decoder for statistical machine translation. In A. Moschitti, B. Pang, W. Daelemans (Eds.), Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) (pp. 1724-1734). Doha, Qatar: Association for Computational Linguistics. doi:10.3115/v1/D14-1179。

He, Q., Pei, J., Kifer, D., Mitra, P., & Giles, L. (2010). Context-aware citation recommendation. In WWW’10: Proceedings of the 19th International Conference on World Wide Web (pp. 421-430). New York, NY: Association for Computing Machinery. doi:10.1145/1772690.1772734。

Huang, W., Kataria, S., Caragea, C., Mitra, P., Giles, C. L., & Rokach, L. (2012). Recommending citations: Translating papers into references. In CIKM’12: Proceedings of the 21st ACM International Conference on Information and Knowledge Management (pp. 1910-1914). New York, NY: Association for Computing Machinery. doi:10.1145/2396761.2398542。

Lee, H., Ahn, Y., Lee, H., Ha, S., & Lee, S.-g. (2016). Quote recommendation in dialogue using deep neural network. In SIGIR ’16: Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 957-960). New York, NY: Association for Computing Machinery. doi:10.1145/2911451.2914734。

Liu, Y., Liu, B., Shan, L., & Wang, X. (2018). Modelling context with neural networks for recommending idioms in essay writing. Neurocomputing, 275, 2287-2293. doi:10.1016/j.neucom.2017.11.005。