生成模型在层次结构极限多标签文本分类中的应用(Generation Model for Hierarchical Extreme Multi-label Text Classification)
Linqing Chen (陈林卿), Dawang He (何大望), Yansi Xiao (肖燕思), Yilin Liu (刘依林), Jianping Lu (陆剑平), Weilei Wang (王为磊)
Abstract
“层次结构极限多标签文本分类是自然语言处理研究领域中一个重要而又具有挑战性的课题。该任务类别标签数量巨大且自成体系,标签与标签之间还具有不同层级间的依赖关系或同层次间的相关性,这些特性进一步增加了任务难度。该文提出将层次结构极限多标签文本分类任务视为序列转换问题,将输出标签视为序列,从而可以直接从数十万标签中生成与文本相关的类别标签。通过软约束机制和词表复合映射在解码过程中利用标签之间的层次结构与相关信息。实验结果表明,该文提出的方法与基线模型相比取得了有意义的性能提升。进一步分析表明,该方法不仅可以捕获利用不同层级标签之间的上下位关系,还对极限多标签体系自身携带的噪声具有一定容错能力。”- Anthology ID:
- 2022.ccl-1.60
- 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:
- 671–683
- Language:
- Chinese
- URL:
- https://aclanthology.org/2022.ccl-1.60
- DOI:
- Cite (ACL):
- Linqing Chen, Dawang He, Yansi Xiao, Yilin Liu, Jianping Lu, and Weilei Wang. 2022. 生成模型在层次结构极限多标签文本分类中的应用(Generation Model for Hierarchical Extreme Multi-label Text Classification). In Proceedings of the 21st Chinese National Conference on Computational Linguistics, pages 671–683, Nanchang, China. Chinese Information Processing Society of China.
- Cite (Informal):
- 生成模型在层次结构极限多标签文本分类中的应用(Generation Model for Hierarchical Extreme Multi-label Text Classification) (Chen et al., CCL 2022)
- PDF:
- https://preview.aclanthology.org/ingest-acl-2023-videos/2022.ccl-1.60.pdf