.png){kind=icon}
.png){kind=icon}
Return
MSnet: Multi-Head Self-Attention Network for Distantly Supervised Relation Extraction
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2019.2913316.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Distant supervision for relation extraction is a task of recognizing semantic relations between entities in a large amount of plain text weakly supervised by external knowledge bases, which can benefit many NLP applications, such as knowledge graph completion and question answering. While it significantly alleviates the expensive cost for data labeling, it severely suffers from noisy labels. In this paper, we propose a Multi-head Self-attention Network (MSNet)-based label denoising method for relation extraction. More specifically, we encode the words, entities and their positions information into contextual embeddings via a multi-head self-attention mechanism, then extract the discriminative sentence features with max pooling operation. MSNet can capture the inherent structure of a sentence and model the relatedness between two words without regard to their distance. Moreover, we adopt a novel label confidence learning method to correct the noisy labels. A latent label is predicted step by step during training as the ground-truth according to a curriculum function of label confidence. This label denoising mechanism gradually incorporates the obtained latent label of easy relation patterns into later latent label prediction of hard patterns, which makes latent label consistent learning more reliable. To verify the effectiveness of our proposed method, in addition to the widely used PCNN-based architecture, we also perform the experiment on BiLSTM model as a comparison. The results demonstrate that our approach can outperform the state-of-the-art systems on the popular evaluation dataset.
Keywords:
Relation extraction
distant supervision
multi-head self-attention
label denoising
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3.6
Papers:
9.8W
Citations:
29.4W