Back to Search
Start Over
Ancient poetry generation with an unsupervised method.
- Source :
- Neural Computing & Applications; Jun2022, Vol. 34 Issue 11, p8525-8538, 14p
- Publication Year :
- 2022
-
Abstract
- It is challenging to use unsupervised machine translation models to generate ancient poems. The current method has solved the problems of Under-translation and Over-translation caused by the huge length difference between the translated sentence pairs. However, the above method lacks guidance in generating intermediate vectors, and the denoising ability of the model is very poor. In this paper, we guide vector space distribution during training to improve the quality of the generated ancient poems and the convergence speed of the model. We also introduce the target language information while adding noise, which effectively avoids the recurrence of the Under-translation problem while improving the model's denoising ability. Experiment results on the VP dataset show that our model obtains state-of-the-art results with faster convergence speed. In addition to the BLEU scores, we also made a comparative analysis of ancient poetry sentences generated by different models. The analysis results show that the optimization method proposed in this paper is indeed helpful for generating high-quality ancient poems. [ABSTRACT FROM AUTHOR]
- Subjects :
- MACHINE translating
VECTOR spaces
POETRY (Literary form)
PROBLEM solving
Subjects
Details
- Language :
- English
- ISSN :
- 09410643
- Volume :
- 34
- Issue :
- 11
- Database :
- Complementary Index
- Journal :
- Neural Computing & Applications
- Publication Type :
- Academic Journal
- Accession number :
- 156859322
- Full Text :
- https://doi.org/10.1007/s00521-021-06571-w