# Chinese Poetry Generation with a Working Memory Model

arXiv: https://arxiv.org/abs/1809.04306 · HTML: https://mlsanity.com/paper/1809.04306/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Sep 2018.

## Built on by (most cited first, 7 of 7)

- [CharPoet: A Chinese Classical Poetry Generation System Based on Token-free LLM](https://mlsanity.com/paper/2401.03512/) (2024)
- [Can AI Write Classical Chinese Poetry like Humans? An Empirical Study Inspired by Turing Test](https://mlsanity.com/paper/2401.04952/) (2024)
- [PWESuite: Phonetic Word Embeddings and Tasks They Facilitate](https://mlsanity.com/paper/2304.02541/) (2023)
- [Multi-Modal Experience Inspired AI Creation](https://mlsanity.com/paper/2209.02427/) (2022)
- [PoeTone: A Framework for Constrained Generation of Structured Chinese Songci with LLMs](https://mlsanity.com/paper/2508.02515/) (2025)
- [There Once Was a Really Bad Poet, It Was Automated but You Didn't Know It](https://mlsanity.com/paper/2103.03775/) (2021)
- [Seeing the Poem: Image-Semantic Detection of AI-Generated Modern Chinese Poetry with MLLMs](https://mlsanity.com/paper/2605.22654/) (2026)

## Abstract (arXiv)

As an exquisite and concise literary form, poetry is a gem of human culture. Automatic poetry generation is an essential step towards computer creativity. In recent years, several neural models have been designed for this task. However, among lines of a whole poem, the coherence in meaning and topics still remains a big challenge. In this paper, inspired by the theoretical concept in cognitive psychology, we propose a novel Working Memory model for poetry generation. Different from previous methods, our model explicitly maintains topics and informative limited history in a neural memory. During the generation process, our model reads the most relevant parts from memory slots to generate the current line. After each line is generated, it writes the most salient parts of the previous line into memory slots. By dynamic manipulation of the memory, our model keeps a coherent information flow and learns to express each topic flexibly and naturally. We experiment on three different genres of Chinese poetry: quatrain, iambic and chinoiserie lyric. Both automatic and human evaluation results show that our model outperforms current state-of-the-art methods.