# Lingxi: A Diversity-aware Chinese Modern Poetry Generation System

arXiv: https://arxiv.org/abs/2108.12108 · HTML: https://mlsanity.com/paper/2108.12108/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 34 references that are in the map.
- First posted on arXiv 27 Aug 2021.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates](https://mlsanity.com/paper/1804.10959/) (2018)
- [Texygen: A Benchmarking Platform for Text Generation Models](https://mlsanity.com/paper/1802.01886/) (2018)
- [Deep Reinforcement Learning for Dialogue Generation](https://mlsanity.com/paper/1606.01541/) (2016)
- [Style Transfer from Non-Parallel Text by Cross-Alignment](https://mlsanity.com/paper/1705.09655/) (2017)
- [Challenges in Data-to-Document Generation](https://mlsanity.com/paper/1707.08052/) (2017)
- [Learning to Write with Cooperative Discriminators](https://mlsanity.com/paper/1805.06087/) (2018)
- [Generating Informative and Diverse Conversational Responses via Adversarial Information Maximization](https://mlsanity.com/paper/1809.05972/) (2018)
- [Trading Off Diversity and Quality in Natural Language Generation](https://mlsanity.com/paper/2004.10450/) (2020)
- [Improved Natural Language Generation via Loss Truncation](https://mlsanity.com/paper/2004.14589/) (2020)
- [A Systematic Characterization of Sampling Algorithms for Open-ended Language Generation](https://mlsanity.com/paper/2009.07243/) (2020)
- [Image Inspired Poetry Generation in XiaoIce](https://mlsanity.com/paper/1808.03090/) (2018)
- [A Graph-based Model for Joint Chinese Word Segmentation and Dependency Parsing](https://mlsanity.com/paper/1904.04697/) (2019)
- [Improving Diversity of Neural Text Generation via Inverse Probability Weighting](https://mlsanity.com/paper/2103.07649/) (2021)
- [Attention Is All You Need for Chinese Word Segmentation](https://mlsanity.com/paper/1910.14537/) (2019)

## Built on by (most cited first, 4 of 4)

- [Creative Data Generation: A Review Focusing on Text and Poetry](https://mlsanity.com/paper/2305.08493/) (2023)
- [A survey of diversity quantification in natural language processing: The why, what, where and how](https://mlsanity.com/paper/2507.20858/) (2025)
- [Detecting Spelling and Grammatical Anomalies in Russian Poetry Texts](https://mlsanity.com/paper/2505.04507/) (2025)
- [A Diversity Diet for a Healthier Model: A Case Study of French ModernBERT](https://mlsanity.com/paper/2602.22014/) (2026)

## Abstract (arXiv)

Poetry generation has been a difficult task in natural language processing. Unlike plain neural text generation tasks, poetry has a high requirement for novelty, since an easily-understood sentence with too many high frequency words might not be considered as poetic, while adequately ambiguous sentences with low frequency words can possibly be novel and creative. Inspired by this, we present Lingxi, a diversity-aware Chinese modern poetry generation system. We propose nucleus sampling with randomized head (NS-RH) algorithm, which randomizes the high frequency part ("head") of the predicted distribution, in order to emphasize on the "comparatively low frequency" words. The proposed algorithm can significantly increase the novelty of generated poetry compared with traditional sampling methods. The permutation of distribution is controllable by tuning the filtering parameter that determines the "head" to permutate, achieving diversity-aware sampling. We find that even when a large portion of filtered vocabulary is randomized, it can actually generate fluent poetry but with notably higher novelty. We also propose a semantic-similarity-based rejection sampling algorithm, which creates longer and more informative context on the basis of the short input poetry title while maintaining high semantic similarity to the title, alleviating the off-topic issue.