# Chinese Song Iambics Generation with Neural Attention-based Model

arXiv: https://arxiv.org/abs/1604.06274 · HTML: https://mlsanity.com/paper/1604.06274/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Apr 2016.

## Built on by (most cited first, 9 of 9)

- [FUDGE: Controlled Text Generation With Future Discriminators](https://mlsanity.com/paper/2104.05218/) (2021)
- [Automatic Song Translation for Tonal Languages](https://mlsanity.com/paper/2203.13420/) (2022)
- [SP-GPT2: Semantics Improvement in Vietnamese Poetry Generation](https://mlsanity.com/paper/2110.15723/) (2021)
- [Text Analysis Using Deep Neural Networks in Digital Humanities and Information Science](https://mlsanity.com/paper/2307.16217/) (2023)
- [Generate and Revise: Reinforcement Learning in Neural Poetry](https://mlsanity.com/paper/2102.04114/) (2021)
- [Vietnamese Poem Generation & The Prospect Of Cross-Language Poem-To-Poem Translation](https://mlsanity.com/paper/2401.01078/) (2024)
- [POEMetric: The Last Stanza of Humanity](https://mlsanity.com/paper/2604.03695/) (2026)
- [AfriKI: Machine-in-the-Loop Afrikaans Poetry Generation](https://mlsanity.com/paper/2103.16190/) (2021)
- [A General Framework for Learning Prosodic-Enhanced Representation of Rap Lyrics](https://mlsanity.com/paper/2103.12615/) (2021)

## Abstract (arXiv)

Learning and generating Chinese poems is a charming yet challenging task. Traditional approaches involve various language modeling and machine translation techniques, however, they perform not as well when generating poems with complex pattern constraints, for example Song iambics, a famous type of poems that involve variable-length sentences and strict rhythmic patterns. This paper applies the attention-based sequence-to-sequence model to generate Chinese Song iambics. Specifically, we encode the cue sentences by a bi-directional Long-Short Term Memory (LSTM) model and then predict the entire iambic with the information provided by the encoder, in the form of an attention-based LSTM that can regularize the generation process by the fine structure of the input cues. Several techniques are investigated to improve the model, including global context integration, hybrid style training, character vector initialization and adaptation. Both the automatic and subjective evaluation results show that our model indeed can learn the complex structural and rhythmic patterns of Song iambics, and the generation is rather successful.