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.
Similar content being viewed by others
References
Yi X, Sun M, Li R, Yang Z (2018) Chinese Poetry Generation with a Working Memory Model. In: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, 4553–4559
Lample G, Denoyer L, Ranzato MA (2018) Unsupervised Machine Translation Using Monolingual Corpora Only. arXiv:1711.00043
Yang Z, Cai P, Feng Y, Li F, Feng W, Chiu EY, Yu H (PMC7255431) Generating Classical Chinese Poems from Vernacular Chinese. In: Proceedings of the conference on empirical methods in natural language processing. Conference on empirical methods in natural language processing, Nov 2019. pp 6155–6164. https://doi.org/10.18653/v1/d19-1637
Artetxe M, Labaka G, Agirre E, Cho K (2018) Unsupervised Neural Machine Translation. arXiv:1710.11041
Och FJ, Ney H (2003) A systematic comparison of various statistical alignment models. Comput Linguist 29(1):19–51
Bahdanau D, Cho K, Bengio Y (2014) Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473
Ji Y, Zhang H, Zhang Z, Liu M (2021) CNN-based encoder-decoder networks for salient object detection: A comprehensive review and recent advances. Information Sciences 546:835–857 %@ 0020–0255
Cho K, Van Merriënboer B, Gulcehre C, Bahdanau D, Bougares F, Schwenk H, Bengio Y (2014) Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078
Kalchbrenner N, Blunsom P (2013) Recurrent continuous translation models. In: EMNLP. pp 1700–1709
Luong M-T, Sutskever I, Le QV, Vinyals O, Zaremba W (2014) Addressing the rare word problem in neural machine translation. arXiv preprint arXiv:1410.8206
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is All you Need. In: NIPS. pp 5998--6008
Devlin J, Chang M-W, Lee K, Toutanova K (2018) Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805
Mehta S, Ghazvininejad M, Iyer S, Zettlemoyer L, Hajishirzi H (2020) DeLighT: Very Deep and Light-weight Transformer. arXiv preprint arXiv:2008.00623
Zhu J, Xia Y, Wu L, He D, Qin T, Zhou W, Li H, Liu T-Y (2020) Incorporating bert into neural machine translation. arXiv preprint arXiv:2002.06823
Zhang Z, Ren S, Liu S, Wang J, Chen P, Li M, Zhou M, Chen E (2018) Style Transfer as Unsupervised Machine Translation. arXiv:1808.07894
Hämäläinen M, Hengchen S (2019) From the Paft to the Fiiture: a Fully Automatic NMT and Word Embeddings Method for OCR Post-Correction. In: RANLP
Weng W-H, Chung Y-A, Szolovits P (2019) Unsupervised clinical language translation. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
Conneau A, Lample G, Ranzato MA, Denoyer L, Jégou H (2018) Word Translation Without Parallel Data. arXiv:1710.04087
Artetxe M, Labaka G, Agirre E (2018) A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings. In: ACL. pp. 789–798
Wan Y, Yang B, Wong DF, Chao LS, Du H (2020) Ao BCH Unsupervised Neural Dialect Translation with Commonality and Diversity Modeling. In: AAAI
He J, Zhou M, Jiang L (2012) Generating Chinese classical poems with statistical machine translation models. In: AAAI, 1650–1656
Yi X, Li R, Sun M (2017) Generating Chinese classical poems with RNN Encoder-Decoder. arXiv:1604.01537
Zhang J, Feng Y, Wang D, Wang Y, Abel A, Zhang S, Zhang A (2017) Flexible and Creative Chinese Poetry Generation Using Neural Memory. arXiv:1705.03773
Yi X, Sun M, Li R, Li W (2018) Automatic Poetry Generation with Mutual Reinforcement Learning. In: EMNLP. 3143–3153
Yang X, Lin X, Suo S, Li M (2018) Generating Thematic Chinese Poetry using Conditional Variational Autoencoders with Hybrid Decoders. In: IJCAI, 4539–4545
Vincent P, Larochelle H, Bengio Y, Manzagol P-A (2008) Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th international conference on Machine learning. 1096–1103
Hill F, Cho K, Korhonen (2016) A learning distributed representations of sentences from Unlabelled Data. In: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, San Diego, California. 1367–1377
Sennrich R, Haddow B, Birch A (2016) Improving Neural Machine Translation Models with Monolingual Data. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, Berlin, Germany. 86–96
Chang P-C, Galley M, Manning CD (2008) Optimizing Chinese Word Segmentation for Machine Translation Performance. In: Proceedings of the Third Workshop on Statistical Machine Translation. 224–232
Rennie SJ, Marcheret E, Mroueh Y, Ross J, Goel V (2017) Self-Critical Sequence Training for Image Captioning. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR):1179–1195
Wu Y, Schuster M, Chen Z, Le QV, Norouzi M, Macherey W, Krikun M, Cao Y, Gao Q, Macherey K, Klingner J, Shah A, Johnson M, Liu X, Kaiser L, Gouws S, Kato Y, Kudo T, Kazawa H, Stevens K, Kurian G, Patil N, Wang W, Young C, Smith J, Riesa J, Rudnick A, Vinyals O, Corrado GS, Hughes M, Dean J (2016) Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation. arXiv:1609.08144
Yang Z, Chen W, Wang F, Xu B (2018) Unsupervised Neural Machine Translation with Weight Sharing. In: ACL. 46–55
Kingma DP, Ba J (2015) Adam: A Method for Stochastic Optimization. CoRR abs/1412.6980
Papineni K, Roukos S, Ward T, Zhu W-J (2002) Bleu: a Method for Automatic Evaluation of Machine Translation. In: ACL. 311–318
Acknowledgements
The authors wish to thank the reviewers for their helpful comments. This work is supported by The National Key Research and Development Program of China (2018YFB0204301).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
We declare that we have no financial and personal relationships with other people or organizations that can inappropriately influence our work, there is no professional or other personal interest of any nature or kind in any product, service and/or company that could be construed as influencing the position presented in, or the review of, the manuscript entitled “Ancient Poetry Generation with an Unsupervised Method.”
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix: Examples of Generated Poems
Appendix: Examples of Generated Poems
Table 10 is some examples of the achievements generated by our model. The content in the table proves that the ancient poems generated in this paper are very close to the professional level.
Rights and permissions
About this article
Cite this article
Zhang, Z., Zhang, H., Wan, Q. et al. Ancient poetry generation with an unsupervised method. Neural Comput & Applic 34, 8525–8538 (2022). https://doi.org/10.1007/s00521-021-06571-w
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-021-06571-w