意合图:中文多层次语义表示方法∗(Parataxis Graph: Multi-level Semantic Representation Method for Chinese)

Guo Mengxi (郭梦溪), Xun Endong (恩东 荀), Li Meng (李梦), Rao Gaoqi (高琦 饶)


Abstract
“基于参数的语义表示虽取得成就,但符号化的语义表示仍具有不可忽视的意义。我们在语义学基础上,充分考虑符号化语义表示在NLP领域落地中的需求,提出了一种兼具通用性与扩展性的多层次语义表示方法——意合图。意合图以事件为核心,由事件结构与实体结构构成,通过多层次语义体系设计,提升与场景结合的能力,并力求对不同层级的语言单元作一贯式表示。在资源建设和相关分析实验中取得良好效果。本文将重点介绍意合图设计理念与多层次语义体系。”
Anthology ID:
2024.ccl-1.58
Volume:
Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)
Month:
July
Year:
2024
Address:
Taiyuan, China
Editors:
Maosong Sun, Jiye Liang, Xianpei Han, Zhiyuan Liu, Yulan He
Venue:
CCL
SIG:
Publisher:
Chinese Information Processing Society of China
Note:
Pages:
740–749
Language:
Chinese
URL:
https://aclanthology.org/2024.ccl-1.58/
DOI:
Bibkey:
Cite (ACL):
Guo Mengxi, Xun Endong, Li Meng, and Rao Gaoqi. 2024. 意合图:中文多层次语义表示方法∗(Parataxis Graph: Multi-level Semantic Representation Method for Chinese). In Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference), pages 740–749, Taiyuan, China. Chinese Information Processing Society of China.
Cite (Informal):
意合图:中文多层次语义表示方法∗(Parataxis Graph: Multi-level Semantic Representation Method for Chinese) (Mengxi et al., CCL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.ccl-1.58.pdf