返回
Exploring Interactive and Contrastive Relations for Nested Named Entity Recognition
DOI:10.1109/TASLP.2023.3293047.png)
摘要
En 中文
Nested named entities (nested NEs) refer to the situation where one named entity is included or nested within another named entity, which cannot be recognized by the traditional sequence labeling methods. Recently, span-based methods have become the mainstream methods for nested Named Entity Recognition (nested NER). The fundamental concept behind this method is to enumerate nearly all potential spans as entity mentions and subsequently classify them. However, span-based methods independently classify spans without considering the semantic relations among them, which negatively impacts the span representation. To address the issue, we propose a novel deep learning architecture for nested NER that explores interactive and contrastive relations among spans. Specifically, we design a scale transformation mechanism that embeds geometric information into span representations, which enhances the model's ability to encode interactive relations between spans. Additionally, we introduce a supervised contrastive learning loss that pulls apart highly overlapping spans in the embedding space to encode the contrastive relations. Experiments show that our method achieves state-of-the-art or competitive performance on three publicly nested NER datasets, thus validating its effectiveness.
Keyword:
Interactive relation
contrastive relation
nested named entity recognition
期刊
I
IF:
5.1
论文数:
2.6K
被引数:
1.1W
机构
引用论文
Group-based intervention to improve developmental status among children age 6–18 months in rural Shanxi province, China: a study protocol for a cluster randomised controlled trial
BMJ Open
IF0
Selection of hybrid plants obtained by electrofusion of vacuolated × evacuolated plant protoplasts in hypo-osmolar solution在低渗溶液中通过电融合获得的液泡化×去液泡化植物原生质体制备杂交植物的筛选
Vesicle formation during electro-fusion of mesophyll protoplasts of Kalancho� daigremontiana大叶景细胞质体电融合过程中的囊泡形成
Planta
IF0

