基于预训练及控制码法的藏文律诗自动生成方法(Automatic Generation of Tibetan Poems based on Pre-training and Control Code Method)

Jia Secha (色差甲), Jiacuo Cizhen (慈祯嘉措), Jia Cairang (才让加), Cairang Huaguo (华果才让)


Abstract
“诗歌自动写作研究是自然语言生成的一个重要研究领域,被认为是极具挑战且有趣的任务之一。本文提出一种基于预训练及控制码法的藏文律诗生成方法。在藏文预训练语言模型上进行微调后生成质量显著提升,然而引入控制码法后在很大程度上确保了扣题程度,即关键词在生成诗作中的平均覆盖率居高。此外,在生成诗作中不仅提高词汇的丰富性,而且生成结果的多样性也明显提升。经测试表明,基于预训练及控制码法的生成方法显著优于基线方法。”
Anthology ID:
2022.ccl-1.33
Volume:
Proceedings of the 21st Chinese National Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Nanchang, China
Editors:
Maosong Sun (孙茂松), Yang Liu (刘洋), Wanxiang Che (车万翔), Yang Feng (冯洋), Xipeng Qiu (邱锡鹏), Gaoqi Rao (饶高琦), Yubo Chen (陈玉博)
Venue:
CCL
SIG:
Publisher:
Chinese Information Processing Society of China
Note:
Pages:
366–373
Language:
Chinese
URL:
https://aclanthology.org/2022.ccl-1.33
DOI:
Bibkey:
Cite (ACL):
Jia Secha, Jiacuo Cizhen, Jia Cairang, and Cairang Huaguo. 2022. 基于预训练及控制码法的藏文律诗自动生成方法(Automatic Generation of Tibetan Poems based on Pre-training and Control Code Method). In Proceedings of the 21st Chinese National Conference on Computational Linguistics, pages 366–373, Nanchang, China. Chinese Information Processing Society of China.
Cite (Informal):
基于预训练及控制码法的藏文律诗自动生成方法(Automatic Generation of Tibetan Poems based on Pre-training and Control Code Method) (Secha et al., CCL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.ccl-1.33.pdf