Generating Classical Chinese Poems from Vernacular Chinese

Classical Chinese poetry is a jewel in the treasure house of Chinese culture. Previous poem generation models only allow users to employ keywords to interfere the meaning of generated poems, leaving the dominion of generation to the model. In this paper, we propose a novel task of generating classical Chinese poems from vernacular, which allows users to have more control over the semantic of generated poems. We adapt the approach of unsupervised machine translation (UMT) to our task. We use segmentation-based padding and reinforcement learning to address under-translation and over-translation respectively. According to experiments, our approach significantly improve the perplexity and BLEU compared with typical UMT models. Furthermore, we explored guidelines on how to write the input vernacular to generate better poems. Human evaluation showed our approach can generate high-quality poems which are comparable to amateur poems.

[1]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[2]  Maosong Sun,et al.  Stylistic Chinese Poetry Generation via Unsupervised Style Disentanglement , 2018, EMNLP.

[3]  Enhong Chen,et al.  Chinese Poetry Generation with Planning based Neural Network , 2016, COLING.

[4]  Yang Feng,et al.  Unsupervised Image Captioning , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Christopher D. Manning,et al.  Optimizing Chinese Word Segmentation for Machine Translation Performance , 2008, WMT@ACL.

[6]  Mirella Lapata,et al.  Chinese Poetry Generation with Recurrent Neural Networks , 2014, EMNLP.

[7]  Guillaume Lample,et al.  Phrase-Based & Neural Unsupervised Machine Translation , 2018, EMNLP.

[8]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[9]  Peter Szolovits,et al.  Unsupervised Clinical Language Translation , 2019, KDD.

[10]  Richard Socher,et al.  A Deep Reinforced Model for Abstractive Summarization , 2017, ICLR.

[11]  Adam Lopez,et al.  Towards speech-to-text translation without speech recognition , 2017, EACL.

[12]  Zhiguo Wang,et al.  Coverage Embedding Models for Neural Machine Translation , 2016, EMNLP.

[13]  Yang Liu,et al.  Modeling Coverage for Neural Machine Translation , 2016, ACL.

[14]  Vaibhava Goel,et al.  Self-Critical Sequence Training for Image Captioning , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  George Kurian,et al.  Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation , 2016, ArXiv.

[16]  Enhong Chen,et al.  Style Transfer as Unsupervised Machine Translation , 2018, ArXiv.

[17]  Yaser Al-Onaizan,et al.  Temporal Attention Model for Neural Machine Translation , 2016, ArXiv.

[18]  Long Jiang,et al.  Generating Chinese Classical Poems with Statistical Machine Translation Models , 2012, AAAI.

[19]  Guillaume Lample,et al.  Unsupervised Machine Translation Using Monolingual Corpora Only , 2017, ICLR.

[20]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[21]  Salim Roukos,et al.  Bleu: a Method for Automatic Evaluation of Machine Translation , 2002, ACL.

[22]  Maosong Sun,et al.  Chinese Poetry Generation with a Working Memory Model , 2018, IJCAI.

[23]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[24]  Chuan Qin,et al.  How Images Inspire Poems: Generating Classical Chinese Poetry from Images with Memory Networks , 2018, AAAI.

[25]  Rui Yan,et al.  i, Poet: Automatic Poetry Composition through Recurrent Neural Networks with Iterative Polishing Schema , 2016, IJCAI.