In recent years, deep learning has been widely applied in relation extraction task. The method uses only word embeddings as network input, and can model relations between target named entity pairs. It equally deals with each relation mention, so it cannot effectively extract relations from the corpus with an enormous number of non-relations, which is the main reason why the performance of relation extraction is significantly lower than that of relation classification. This paper designs a deep reinforcement learning framework for relation extraction, which considers relation extraction task as a two-step decision-making game. The method models relation mentions with CNN and Tree-LSTM, which can calculate initial state and transition state for the game respectively. In addition, we can tackle the problem of unbalanced corpus by designing penalty function which can increase the penalties for first-step decision-making errors. Finally, we use Q-Learning algorithm with value function approximation to learn control policy π for the game. This paper sets up a series of experiments in ACE2005 corpus, which show that the deep reinforcement learning framework can achieve state-of-the-art performance in relation extraction task.
Hongjun ZHANG
PLA University of Science and Technology
Yuntian FENG
PLA University of Science and Technology
Wenning HAO
PLA University of Science and Technology
Gang CHEN
PLA University of Science and Technology
Dawei JIN
PLA University of Science and Technology
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Hongjun ZHANG, Yuntian FENG, Wenning HAO, Gang CHEN, Dawei JIN, "Relation Extraction with Deep Reinforcement Learning" in IEICE TRANSACTIONS on Information,
vol. E100-D, no. 8, pp. 1893-1902, August 2017, doi: 10.1587/transinf.2016EDP7450.
Abstract: In recent years, deep learning has been widely applied in relation extraction task. The method uses only word embeddings as network input, and can model relations between target named entity pairs. It equally deals with each relation mention, so it cannot effectively extract relations from the corpus with an enormous number of non-relations, which is the main reason why the performance of relation extraction is significantly lower than that of relation classification. This paper designs a deep reinforcement learning framework for relation extraction, which considers relation extraction task as a two-step decision-making game. The method models relation mentions with CNN and Tree-LSTM, which can calculate initial state and transition state for the game respectively. In addition, we can tackle the problem of unbalanced corpus by designing penalty function which can increase the penalties for first-step decision-making errors. Finally, we use Q-Learning algorithm with value function approximation to learn control policy π for the game. This paper sets up a series of experiments in ACE2005 corpus, which show that the deep reinforcement learning framework can achieve state-of-the-art performance in relation extraction task.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2016EDP7450/_p
Copy
@ARTICLE{e100-d_8_1893,
author={Hongjun ZHANG, Yuntian FENG, Wenning HAO, Gang CHEN, Dawei JIN, },
journal={IEICE TRANSACTIONS on Information},
title={Relation Extraction with Deep Reinforcement Learning},
year={2017},
volume={E100-D},
number={8},
pages={1893-1902},
abstract={In recent years, deep learning has been widely applied in relation extraction task. The method uses only word embeddings as network input, and can model relations between target named entity pairs. It equally deals with each relation mention, so it cannot effectively extract relations from the corpus with an enormous number of non-relations, which is the main reason why the performance of relation extraction is significantly lower than that of relation classification. This paper designs a deep reinforcement learning framework for relation extraction, which considers relation extraction task as a two-step decision-making game. The method models relation mentions with CNN and Tree-LSTM, which can calculate initial state and transition state for the game respectively. In addition, we can tackle the problem of unbalanced corpus by designing penalty function which can increase the penalties for first-step decision-making errors. Finally, we use Q-Learning algorithm with value function approximation to learn control policy π for the game. This paper sets up a series of experiments in ACE2005 corpus, which show that the deep reinforcement learning framework can achieve state-of-the-art performance in relation extraction task.},
keywords={},
doi={10.1587/transinf.2016EDP7450},
ISSN={1745-1361},
month={August},}
Copy
TY - JOUR
TI - Relation Extraction with Deep Reinforcement Learning
T2 - IEICE TRANSACTIONS on Information
SP - 1893
EP - 1902
AU - Hongjun ZHANG
AU - Yuntian FENG
AU - Wenning HAO
AU - Gang CHEN
AU - Dawei JIN
PY - 2017
DO - 10.1587/transinf.2016EDP7450
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E100-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 2017
AB - In recent years, deep learning has been widely applied in relation extraction task. The method uses only word embeddings as network input, and can model relations between target named entity pairs. It equally deals with each relation mention, so it cannot effectively extract relations from the corpus with an enormous number of non-relations, which is the main reason why the performance of relation extraction is significantly lower than that of relation classification. This paper designs a deep reinforcement learning framework for relation extraction, which considers relation extraction task as a two-step decision-making game. The method models relation mentions with CNN and Tree-LSTM, which can calculate initial state and transition state for the game respectively. In addition, we can tackle the problem of unbalanced corpus by designing penalty function which can increase the penalties for first-step decision-making errors. Finally, we use Q-Learning algorithm with value function approximation to learn control policy π for the game. This paper sets up a series of experiments in ACE2005 corpus, which show that the deep reinforcement learning framework can achieve state-of-the-art performance in relation extraction task.
ER -