面向中文AMR标注体系的兼语语料库构建及识别研究(Research on the Construction and Recognition of Concurrent corpus for Chinese AMR Annotation System)
Wenhui Hou (侯文惠), Weiguang Qu (曲维光), Tingxin Wei (魏庭新), Bin Li (李斌), Yanhui Gu (顾彦慧), Junsheng Zhou (周俊生)
Abstract
兼语结构是汉语中常见的一种动词结构,由述宾短语与主谓短语共享兼语,结构复杂,给句法分析造成困难,因此兼语语料库构建及识别工作对于语义解析及下游任务都具有重要意义。但现存兼语语料库较少,面向中文AMR标注体系的兼语语料库构建仍处于空白阶段。针对这一现状,本文总结了一套兼语语料库标注规范,并构建了一定数量面向中文AMR标注体系的兼语语料库。基于构建的语料库,采用基于字符的神经网络模型识别兼语结构,并对识别结果以及未来的改进方向进行分析总结。- Anthology ID:
- 2020.ccl-1.49
- Volume:
- Proceedings of the 19th Chinese National Conference on Computational Linguistics
- Month:
- October
- Year:
- 2020
- Address:
- Haikou, China
- Venue:
- CCL
- SIG:
- Publisher:
- Chinese Information Processing Society of China
- Note:
- Pages:
- 528–538
- Language:
- Chinese
- URL:
- https://aclanthology.org/2020.ccl-1.49
- DOI:
- Cite (ACL):
- Wenhui Hou, Weiguang Qu, Tingxin Wei, Bin Li, Yanhui Gu, and Junsheng Zhou. 2020. 面向中文AMR标注体系的兼语语料库构建及识别研究(Research on the Construction and Recognition of Concurrent corpus for Chinese AMR Annotation System). In Proceedings of the 19th Chinese National Conference on Computational Linguistics, pages 528–538, Haikou, China. Chinese Information Processing Society of China.
- Cite (Informal):
- 面向中文AMR标注体系的兼语语料库构建及识别研究(Research on the Construction and Recognition of Concurrent corpus for Chinese AMR Annotation System) (Hou et al., CCL 2020)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/2020.ccl-1.49.pdf