AI helps you reading Science
AI generates interpretation videos
AI extracts and analyses the key points of the paper to generate videos automatically
AI parses the academic lineage of this thesis
AI extracts a summary of this paper
In this paper we presented the first neural poetry translation system and provided two novel methods to improve the quality of the translations
Neural Poetry Translation.
NAACL-HLT, pp.67-71, (2018)
We present the first neural poetry translation system. Unlike previous works that often fail to produce any translation for fixed rhyme and rhythm patterns, our system always translates a source text to an English poem. Human evaluation ranks translation quality as acceptable 78.2% of the time.
PPT (Upload PPT)
- Despite recent improvements in machine translation, automatic translation of poetry remains a challenging problem.
- This challenge is partially due to the intrinsic complexities of translating a poem.
- As Robert Frost says “Poetry is what gets lost in translation”.
- In practice poems have always been translated and will continue to be translated between languages and cultures.
- The authors introduce a method for automatic poetry translation.
- Consider the following French poem: French poem: Puis je venais masseoir pr‘es de sa chaise Pour lui parler le soir plus ‘a mon aise
- Despite recent improvements in machine translation, automatic translation of poetry remains a challenging problem
- We propose the first neural poetry translation system and show its quality in translating French to English poems
- We present the judges with the French poem for reference and did not mention that the poems are computer generated
- In this paper we presented the first neural poetry translation system and provided two novel methods to improve the quality of the translations
- The base of the poetry translation system is an encoderdecoder sequence-to-sequence model (Sutskever et al, 2014) with a two-layer recurrent neural network (RNN) with long short-term memory (LSTM) units (Hochreiter and Schmidhuber, 1997).
- It is pre-trained on parallel French-English WMT14 corpus.2.
- The authors' first experiment compares model A with model B.
- The results in Table 1 clearly show that the model B generates better translations
- In this paper the authors presented the first neural poetry translation system and provided two novel methods to improve the quality of the translations.
- French poem: Il ny avait que sable et boue Ousetait ouverte la tombe.
- Le long des murs de la prison On ne voyait aucune tombe.
- French poem: Tels des vaisseaux dans la tempete, Nos deux chemins setaient croises, Sans młme un signe et sans un mot, Nous navions mot declarer ; Nous netions pas dans la nuit sainte Mais dans le jour deshonore.
- Table1: Users prefer translations generated by model A
- Table2: Users prefer translations generated by model C
- Table3: Quality of the translated poems by model C
- This work was supported in part by DARPA under the CwC program through the ARO (W911NF-15-1-0543), NSF (IIS-1524371), and gifts by Google and Facebook. ems and showed that the proposed improvements highly improve the translation quality
- Dmitriy Genzel, Jakob Uszkoreit, and Franz Och. 2010. Poetic statistical machine translation: rhyme and meter. In Proceedings of EMNLP.
- Marjan Ghazvininejad, Xing Shi, Yejin Choi, and Kevin Knight. 2016. Generating topical poetry. In Proceedings of EMNLP.
- Marjan Ghazvininejad, Xing Shi, Jay Priyadarshi, and Kevin Knight. 2017. Hafez: an interactive poetry generation system. In Proceedings of ACL Demo Track.
- Erica Greene, Tugba Bodrumlu, and Kevin Knight. 2010. Automatic analysis of rhythmic poetry with applications to generation and translation. In Proceedings of EMNLP.
- Jing He, Ming Zhou, and Long Jiang. 2012. Generating Chinese classical poems with statistical machine translation models. In Proceedings of AAAI.
- Sepp Hochreiter and Jurgen Schmidhuber. 1997. Long short-term memory. Neural computation 9(8).
- Jack Hopkins and Douwe Kiela. 201Automatically generating rhythmic verse with neural networks. In Proceedings of ACL.
- Franz Josef Och and Hermann Ney. 2003. A systematic comparison of various statistical alignment models. Computational linguistics 29(1).
- Hugo Oliveira. 2012. PoeTryMe: a versatile platform for poetry generation. Computational Creativity, Concept Invention, and General Intelligence 1.
- Hugo Goncalo Oliveira. 2017. A survey on intelligent poetry generation: Languages, features, techniques, reutilisation and evaluation. In Proceedings of the 10th International Conference on Natural Language Generation.
- Ilya Sutskever, Oriol Vinyals, and Quoc Le. 2014. Sequence to sequence learning with neural networks. In proceedings of NIPS.
- Qixin Wang, Tianyi Luo, Dong Wang, and Chao Xing. 2016. Chinese song iambics generation with neural attention-based model. In Proceedings of IJCAI.
- Oscar Wilde. 2001. Ballad of Reading Gaol. Electric Book Company.
- Rui Yan, Han Jiang, Mirella Lapata, Shou-De Lin, Xueqiang Lv, and Xiaoming Li. 2013. I, Poet: Automatic Chinese poetry composition through a generative summarization framework under constrained optimization. In Proceedings of IJCAI.
- Xiaoyuan Yi, Ruoyu Li, and Maosong Sun. 2017. Generating chinese classical poems with RNN encoderdecoder. In Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data.
- Xingxing Zhang and Mirella Lapata. 2014. Chinese poetry generation with recurrent neural networks. In Proceedings of EMNLP.