Nowadays, neural networks play an important role in the task of relation
classification. By designing different neural architectures, researchers have
improved the performance to a large extent in comparison with traditional
methods. However, existing neural networks for relation classification are
usually of shallow architectures (e.g., one-layer convolutional neural networks
or recurrent networks). They may fail to explore the potential representation
space in different abstraction levels. In this paper, we propose deep recurrent
neural networks (DRNNs) for relation classification to tackle this challenge.
Further, we propose a data augmentation method by leveraging the directionality
of relations. We evaluated our DRNNs on the SemEval-2010 Task~8, and achieve an
F1-score of 86.1%, outperforming previous state-of-the-art recorded results.
Description
Improved Relation Classification by Deep Recurrent Neural Networks with
Data Augmentation
%0 Conference Paper
%1 xu2016improved
%A Xu, Yan
%A Jia, Ran
%A Mou, Lili
%A Li, Ge
%A Chen, Yunchuan
%A Lu, Yangyang
%A Jin, Zhi
%B COLING-16
%D 2016
%K classification networks neural relation rnn
%T Improved Relation Classification by Deep Recurrent Neural Networks with Data Augmentation.
%U http://dblp.uni-trier.de/db/conf/coling/coling2016.html#XuJMLCLJ16
%X Nowadays, neural networks play an important role in the task of relation
classification. By designing different neural architectures, researchers have
improved the performance to a large extent in comparison with traditional
methods. However, existing neural networks for relation classification are
usually of shallow architectures (e.g., one-layer convolutional neural networks
or recurrent networks). They may fail to explore the potential representation
space in different abstraction levels. In this paper, we propose deep recurrent
neural networks (DRNNs) for relation classification to tackle this challenge.
Further, we propose a data augmentation method by leveraging the directionality
of relations. We evaluated our DRNNs on the SemEval-2010 Task~8, and achieve an
F1-score of 86.1%, outperforming previous state-of-the-art recorded results.
@inproceedings{xu2016improved,
abstract = {Nowadays, neural networks play an important role in the task of relation
classification. By designing different neural architectures, researchers have
improved the performance to a large extent in comparison with traditional
methods. However, existing neural networks for relation classification are
usually of shallow architectures (e.g., one-layer convolutional neural networks
or recurrent networks). They may fail to explore the potential representation
space in different abstraction levels. In this paper, we propose deep recurrent
neural networks (DRNNs) for relation classification to tackle this challenge.
Further, we propose a data augmentation method by leveraging the directionality
of relations. We evaluated our DRNNs on the SemEval-2010 Task~8, and achieve an
F1-score of 86.1%, outperforming previous state-of-the-art recorded results.},
added-at = {2017-10-05T22:40:25.000+0200},
author = {Xu, Yan and Jia, Ran and Mou, Lili and Li, Ge and Chen, Yunchuan and Lu, Yangyang and Jin, Zhi},
biburl = {https://www.bibsonomy.org/bibtex/2e8b07c3d61a699e71b68c867deb69eb6/schwemmlein},
booktitle = {COLING-16},
description = {Improved Relation Classification by Deep Recurrent Neural Networks with
Data Augmentation},
interhash = {738fe68ac05f2bebf92d6220beeea94a},
intrahash = {e8b07c3d61a699e71b68c867deb69eb6},
keywords = {classification networks neural relation rnn},
timestamp = {2017-10-06T09:24:58.000+0200},
title = {Improved Relation Classification by Deep Recurrent Neural Networks with Data Augmentation.},
url = {http://dblp.uni-trier.de/db/conf/coling/coling2016.html#XuJMLCLJ16},
year = 2016
}