.png){kind=icon}
返回
Modified R-BERT with global semantic information for relation classification task
.png){kind=icon}
PRE
AI
DOI：10.1016/j.csl.2024.101686.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The objective of the relation classification task is to extract relations between entities. Recent studies have found that R-BERT (Wu and He, 2019) based on pre-trained BERT (Devlin et al., 2019) acquires extremely good results in the relation classification task. However, this method does not take into account the semantic differences between different kinds of entities and global semantic information either. In this paper, we set two different fully connected layers to take into account the semantic difference between subject and object entities. Besides, we build a new module named Concat Module to fully fuse the semantic information among the subject entity vector, object entity vector, and the whole sample sentence representation vector. In addition, we apply the average pooling to acquire a better entity representation of each entity and add the activation operation with a new fully connected layer after our Concat Module. Modifying R-BERT, we propose a new model named BERT with Global Semantic Information (GSR-BERT) for relation classification tasks. We use our approach on two datasets: the SemEval2010 Task 8 dataset and the Chinese character relationship classification dataset. Our approach achieves a significant improvement over the two datasets. It means that our approach enjoys transferability across different datasets. Furthermore, we prove that these policies we used in our approach also enjoy applicability to named entity recognition task.
Keyword:
BERT
Natural language processing
Relation classification
Neural network
期刊
C
IF:
3.4
论文数:
1.5K
被引数:
2.6K
机构
引用论文
.png){kind=icon}
分享收藏BERT-hLSTMs: BERT and hierarchical LSTMs for visual storytellingBert-hlstms: 用于视觉叙事的BERT和分层LSTMs
OAAI
OAAI分享收藏 没有更多内容
没有更多内容