.png){kind=icon}
返回
Document-level relation extraction via commonsense knowledge enhanced graph representation learning
.png){kind=icon}
PRE
AI
DOI：10.1007/s10489-024-05985-y.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Document-level relation extraction (DocRE) aims to reason about complex relational facts among entities by reading, inferring, and aggregating among entities over multiple sentences in a document. Existing studies construct document-level graphs to enrich interactions between entities. However, these methods pay more attention to the entity nodes and their connections, regardless of the rich knowledge entailed in the original corpus.In this paper, we propose a commonsense knowledge enhanced document-level graph representation, called CGDRE, which delves into the semantic knowledge of the original corpus and improves the ability of DocRE. Firstly, we use coreference contrastive learning to capture potential commonsense knowledge. Secondly, we construct a heterogeneous graph to enhance the graph structure information according to the original document and commonsense knowledge. Lastly, CGDRE infers relations on the aggregated graph and uses focal loss to train the model. Remarkably, it is amazing that CGDRE can effectively alleviate the long-tailed distribution problem in DocRE. Experiments on the public datasets DocRED, DialogRE, and MPDD show that CGDRE can significantly outperform other baselines, achieving a significant performance improvement. Extensive analyses demonstrate that the performance of our CGDRE is contributed by the capture of commonsense knowledge enhanced graph relation representation.
Keyword:
Document-level relation extraction
Contrastive learning
Commonsense knowledge
Graph neural network
期刊
IF:
3.5
论文数:
7.7K
被引数:
1.7W
机构
引用论文
An Improved Version of the Extended Velocity-Azimuth Display Analysis of Single-Doppler Radar Data
OAAI
OAAI分享收藏
Matrix Effects in the Detection of Pb and Ba in Soils Using Laser-Induced Breakdown Spectroscopy使用激光诱导击穿光谱检测土壤中Pb和Ba的基质效应
PREAI
分享收藏Mapping past and recent landscape modifications in the Lagoon of Venice through geophysical surveys and historical maps.png)
Anthropocene
AnthropoceneIF0
PREAI
分享收藏
查看更多内容