Type

Conference Proceedings

Authors

Ruihai Dong
Catherine Mooney
James Ng
Tin Lok
Linyi Yang

Subjects

Computer Science

Topics
relation extraction world distant supervision neural networks semantic network methods neural network word level attention

Multi-level Attention-Based Neural Networks for Distant Supervised Relation Extraction (2017)

Abstract We propose a multi-level attention-based neural network forrelation extraction based on the work of Lin et al. to alleviate the problemof wrong labelling in distant supervision. In this paper, we first adoptgated recurrent units to represent the semantic information. Then, weintroduce a customized multi-level attention mechanism, which is expectedto reduce the weights of noisy words and sentences. Experimentalresults on a real-world dataset show that our model achieves significantimprovement on relation extraction tasks compared to both traditionalfeature-based models and existing neural network-based methods
Collections Ireland -> University College Dublin -> Insight Research Collection

Full list of authors on original publication

Ruihai Dong, Catherine Mooney, James Ng, Tin Lok, Linyi Yang

Experts in our system

1
Ruihai Dong
University College Dublin
Total Publications: 19
 
2
Catherine Mooney
University College Dublin
Total Publications: 63
 
3
James Ng
University College Dublin
Total Publications: 3
 
4
Linyi Yang
University College Dublin
Total Publications: 3