融合多粒度特征的低资源语言词性标记和依存分析联合模型(A Joint Model with Multi-Granularity Features of Low-resource Language POS Tagging and Dependency Parsing)

Sha Lu (陆杉), Cunli Mao (毛存礼), Zhengtao Yu (余正涛), Chengxiang Gao (高盛祥), Yuxin Huang (黄于欣), Zhenhan Wang (王振晗)


Abstract
研究低资源语言的词性标记和依存分析对推动低资源自然语言处理任务有着重要的作用。针对低资源语言词嵌入表示,已有工作并没有充分利用字符、子词层面信息编码,导致模型无法利用不同粒度的特征,对此,提出融合多粒度特征的词嵌入表示,利用不同的语言模型分别获得字符、子词以及词语层面的语义信息,将三种粒度的词嵌入进行拼接,达到丰富语义信息的目的,缓解由于标注数据稀缺导致的依存分析模型性能不佳的问题。进一步将词性标记和依存分析模型进行联合训练,使模型之间能相互共享知识,降低词性标记错误在依存分析任务上的线性传递。以泰语、越南语为研究对象,在宾州树库数据集上,提出方法相比于基线模型的UAS、LAS、POS均有明显提升。
Anthology ID:
2021.ccl-1.67
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:
747–757
Language:
Chinese
URL:
https://aclanthology.org/2021.ccl-1.67
DOI:
Bibkey:
Cite (ACL):
Sha Lu, Cunli Mao, Zhengtao Yu, Chengxiang Gao, Yuxin Huang, and Zhenhan Wang. 2021. 融合多粒度特征的低资源语言词性标记和依存分析联合模型(A Joint Model with Multi-Granularity Features of Low-resource Language POS Tagging and Dependency Parsing). In Proceedings of the 20th Chinese National Conference on Computational Linguistics, pages 747–757, Huhhot, China. Chinese Information Processing Society of China.
Cite (Informal):
融合多粒度特征的低资源语言词性标记和依存分析联合模型(A Joint Model with Multi-Granularity Features of Low-resource Language POS Tagging and Dependency Parsing) (Lu et al., CCL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.ccl-1.67.pdf