.png){kind=icon}
返回
Low-resource extraction with knowledge-aware pairwise prototype learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.knosys.2021.107584.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Knowledge Extraction (KE) aims at extracting structured information from raw texts, such as relation extraction and event extraction. One of the major issues for KE is the low-resource problem due to deficient samples. Previous work addresses the low-resource issue mostly via data-driven methods, such as transfer learning, while neglecting correlation knowledge among classes. For example, inherent correlation of entailment between the relation pair and causality between the event pair can also be utilized for low-resource KE. Consequently, we propose to leverage correlation knowledge via pairwise prototype learning on the hypersphere with a novel framework called Knowledge-aware Hyperspherical Prototype Network (K-HPN). K-HPN is able to recognize inherent correlation among classes, where each class is represented as a prototype on the hypersphere. The experimental results demonstrate that K-HPN outperforms previous methods of KE, particularly with low-resource training data regimes. (C) 2021 Elsevier B.V. All rights reserved.
Keyword:
Knowledge extraction
Knowledge-aware
Pairwise prototype learning
Low-resource
期刊
K
IF:
7.6
论文数:
1.3W
被引数:
4.8W
机构
引用论文
Neural symbolic reasoning with knowledge graphs: Knowledge extraction, relational reasoning, and inconsistency checking具有知识图的神经符号推理: 知识提取，关系推理和不一致性检查.png)
FUNDAMENTAL RESEARCH
OAAI
FUNDAMENTAL RESEARCHIF6.3
OAAI分享收藏Heterogeneous graph neural networks for noisy few-shot relation classification异类图神经网络在噪声少镜头关系分类中的应用
PREAI
分享收藏 没有更多内容
没有更多内容