Abstract
抽象语义表示(Abstract Meaning Representation,简称AMR)是将给定的文本的语义特征抽象成一个单根的有向无环图。AMR语义解析则是根据输入的文本获取对应的AMR图。相比于英文AMR,中文AMR的研究起步较晚,造成针对中文的AMR语义解析相关研究较少。本文针对公开的中文AMR语料库CAMR1.0,采用序列到序列的方法进行中文AMR语义解析的相关研究。具体地,首先基于Transformer模型实现一个适用于中文的序列到序列AMR语义解析系统;然后,探索并比较了不同预训练模型在中文AMR语义解析中的应用。基于该语料,本文中文AMR语义解析方法最优性能达到了70.29的Smatch F1值。本文是第一次在该数据集上报告实验结果。- Anthology ID:
- 2021.ccl-1.35
- Volume:
- Proceedings of the 20th Chinese National Conference on Computational Linguistics
- Month:
- August
- Year:
- 2021
- Address:
- Huhhot, China
- Editors:
- Sheng Li (李生), Maosong Sun (孙茂松), Yang Liu (刘洋), Hua Wu (吴华), Kang Liu (刘康), Wanxiang Che (车万翔), Shizhu He (何世柱), Gaoqi Rao (饶高琦)
- Venue:
- CCL
- SIG:
- Publisher:
- Chinese Information Processing Society of China
- Note:
- Pages:
- 374–385
- Language:
- Chinese
- URL:
- https://aclanthology.org/2021.ccl-1.35
- DOI:
- Cite (ACL):
- Ziyi Huang, Junhui Li, and Zhengxian Gong. 2021. 基于序列到序列的中文AMR解析(Chinese AMR Parsing based on Sequence-to-Sequence Modeling). In Proceedings of the 20th Chinese National Conference on Computational Linguistics, pages 374–385, Huhhot, China. Chinese Information Processing Society of China.
- Cite (Informal):
- 基于序列到序列的中文AMR解析(Chinese AMR Parsing based on Sequence-to-Sequence Modeling) (Huang et al., CCL 2021)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2021.ccl-1.35.pdf