基于多任务标签一致性机制的中文命名实体识别(Chinese Named Entity Recognition based on Multi-task Label Consistency Mechanism)

Shuning Lv (吕书宁), Jian Liu (刘健), Jinan Xu (徐金安), Yufeng Chen (陈钰枫), Yujie Zhang (张玉洁)


Abstract
实体边界预测对中文命名实体识别至关重要。现有研究为改善边界识别效果提出的多任务学习方法仅考虑与分词任务结合,缺少多任务标签训练数据,无法学到任务的标签一致性关系。本文提出一种新的基于多任务标签一致性机制的中文命名实体识别方法:将分词和词性信息融入命名实体识别模型,使三种任务联合训练;建立基于标签一致性机制的多任务学习模式,来捕获标签一致性关系及学习多任务表示。全样本和小样本实验表明了方法的有效性。
Anthology ID:
2021.ccl-1.52
Volume:
Proceedings of the 20th Chinese National Conference on Computational Linguistics
Month:
August
Year:
2021
Address:
Huhhot, China
Venue:
CCL
SIG:
Publisher:
Chinese Information Processing Society of China
Note:
Pages:
576–588
Language:
Chinese
URL:
https://aclanthology.org/2021.ccl-1.52
DOI:
Bibkey:
Cite (ACL):
Shuning Lv, Jian Liu, Jinan Xu, Yufeng Chen, and Yujie Zhang. 2021. 基于多任务标签一致性机制的中文命名实体识别(Chinese Named Entity Recognition based on Multi-task Label Consistency Mechanism). In Proceedings of the 20th Chinese National Conference on Computational Linguistics, pages 576–588, Huhhot, China. Chinese Information Processing Society of China.
Cite (Informal):
基于多任务标签一致性机制的中文命名实体识别(Chinese Named Entity Recognition based on Multi-task Label Consistency Mechanism) (Lv et al., CCL 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2021.ccl-1.52.pdf