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

Files in This Item:
 File SizeFormat
Downloadinsight_publication.pdf1.34 MBAdobe PDF
Title: Multi-level Attention-Based Neural Networks for Distant Supervised Relation Extraction
Authors: Yang, LinyiNg, Tin Lok JamesMooney, CatherineDong, Ruihai
Permanent link: http://hdl.handle.net/10197/9303
Date: 8-Dec-2017
Online since: 2018-04-09T09:26:20Z
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
Funding Details: Science Foundation Ireland
Type of material: Conference Publication
Publisher: Insight Centre
Keywords: Relation extractionDistant supervisionWord-level attention
Other versions: http://aics2017.dit.ie/papers.html
Language: en
Status of Item: Peer reviewed
Conference Details: 25th Irish Conference on Artificial Intelligence and Cognitive Science, Dublin, Ireland, 7-8 December 2017
This item is made available under a Creative Commons License: https://creativecommons.org/licenses/by-nc-nd/3.0/ie/
Appears in Collections:Insight Research Collection

Show full item record

Page view(s)

787
Last Week
2
Last month
12
checked on Jun 26, 2022

Download(s)

194
checked on Jun 26, 2022

Google ScholarTM

Check


If you are a publisher or author and have copyright concerns for any item, please email research.repository@ucd.ie and the item will be withdrawn immediately. The author or person responsible for depositing the article will be contacted within one business day.