Best from Top k Versus Top 1:Improving Distant Supervision Relation Extraction with Deep Reinforcement Learning
Distant supervision relation extraction is a promising approach to find new relation instances from large text corpora.Most previous works employ the top 1 strategy,i.e.,predicting the relation of a sentence with the highest confidence score,which is not always the optimal solution.To improve distant supervision relation extraction,this work applies the best from top k strategy to explore the possibility of relations with lower confidence scores.We approach the best from top k strategy using a deep reinforcement learning framework,where the model learns to select the optimal relation among the top k candidates for better predictions.Specifically,we employ a deep Q-network,trained to optimize a reward function that reflects the extraction performance under distant supervision.The experiments on three public datasets-of news articles,Wikipedia and biomedical papers-demonstrate that the proposed strategy improves the performance of traditional state-of-the-art relation extractors significantly.We achieve an improvement of 5.13%in average F1-score over four competitive baselines.
Distant supervision Relation extraction Deep reinforcement learning Deep Q-networks
Yaocheng Gui Qian Liu Tingming Lu Zhiqiang Gao
School of Computer Science and Engineering,Southeast University,Nanjing,China School of Computer Science and Technology,Nanjing University of Posts and Telecommunications,Nanjing
国际会议
澳门
英文
199-211
2019-04-14（万方平台首次上网日期，不代表论文的发表时间）