paper-with-me

Papers

Lingxi: A Diversity-aware Chinese Modern Poetry Generation System

2021-08-27 · Xinran Zhang, Maosong Sun, Jiafeng Liu, Xiaobing Li

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.

📄 PDF Abstract BibTeX arXiv:2108.12108

Code (0)

등록된 구현이 없습니다.

Tasks

DiversitySemantic SimilaritySemantic Textual SimilaritySentenceText Generation

Similar Papers 제목 키워드 기반

Compose Like Humans: Jointly Improving the Coherence and Novelty for Modern Chinese Poetry Generation

2020-05-04 · Lei Shen, XIAOYU GUO, Meng Chen

Chinese poetry is an important part of worldwide culture, and classical and modern sub-branches are quite different. The former is a unique genre and has strict constraints, while the latter is very flexible in length, o…

Cultural Vocal Bursts Intensity PredictionDiversityRetrievalSentence

Benchmarking the Detection of LLMs-Generated Modern Chinese Poetry

2025-09-01 · Shanshan Wang, Junchao Wu, Fengying Ye, Jingming Yao 외 arxiv

The rapid development of advanced large language models (LLMs) has made AI-generated text indistinguishable from human-written text. Previous work on detecting AI-generated text has made effective progress, but has not i…

CCPM: A Chinese Classical Poetry Matching Dataset

2021-06-03 · Wenhao Li, Fanchao Qi, Maosong Sun, Xiaoyuan Yi 외

Poetry is one of the most important art forms of human languages. Recently many studies have focused on incorporating some linguistic features of poetry, such as style and sentiment, into its understanding or generation …

Translation

Rhetorically Controlled Encoder-Decoder for Modern Chinese Poetry Generation

2019-07-01 · ACL 2019 7 · Zhi-Qiang Liu, Zuohui Fu, Jie Cao, Gerard de Melo 외

Rhetoric is a vital element in modern poetry, and plays an essential role in improving its aesthetics. However, to date, it has not been considered in research on automatic poetry generation. In this paper, we propose a …

Decoder

Seeing the Poem: Image-Semantic Detection of AI-Generated Modern Chinese Poetry with MLLMs

2026-05-21 · Shanshan Wang, Fengying Ye, Hanjia Lyu, Caiwen Gou 외 arxiv

Previous detection studies have shown that LLMs cannot be effectively used as detectors, but these studies have not addressed modern Chinese poetry. Moreover, no relevant research has explored the performance of LLMs in …