Abstract
AbstractMachine poetry generation has been studied for decades, among which ancient Chinese poetry is still challenging in the field of poetry generation due to its unique regularity and rhythm. The quality improvement of ancient Chinese poetries is one of the most promising research areas of ancient Chinese Natural Language Processing. This paper proposes an ancient Chinese poetry polishing model, which is used for polishing to obtain high-quality ancient Chinese poetry. The model consists of a detection network and a correction network. The detection network based on BiLSTM and CRF is used to detect different types of low-quality words in poems. The correction network based on the BERT model is used to modify the detected low-quality words in the global context. The polishing process is iteratively performed until the model judges that there are no low-quality words in the poem. The results show that the polished poems are improved in multiple evaluations. Compared with existing polishing models, the model proposed in this paper performs better in both automatic evaluation and human evaluation when the number of parameters is reduced.
Funder
National Natural Science Foundation of China
Natural Science Foundation of Jiangsu Province
Publisher
Springer Science and Business Media LLC
Reference22 articles.
1. Devlin, J. Chang, M. Lee, K. Toutanova, (2019) K: BERT: Pre-training of deep bidirectional transformers for language understanding. In: North American Association for Computational Linguistics (NAACL), pp. 4147–4186
2. Gervás P (2001) An expert system for the composition of formal Spanish poetry. Knowl Based Syst 14(3–4):181–188
3. Manurung, H.: (2003) An evolutionary algorithm approach to poetry generation. In: Ph.D. Thesis, University of Edinburgh
4. He, J. Zhou, M. Jiang, L.: (2012) Generating Chinese classical poems with statistical machine translation models. In: Proceedings of the 26th AAAI Conference on Artificial Intelligence, pp. 1650–1656
5. Zhang, X. Lapata, M.: (2014) Chinese poetry generation with recurrent neural networks. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, pp. 670–680