RH-Net: Improving Neural Relation Extraction via Reinforcement Learning and Hierarchical Relational Searching

27 Oct 2020  ·  Jianing Wang ·

Distant supervision (DS) aims to generate large-scale heuristic labeling corpus, which is widely used for neural relation extraction currently. However, it heavily suffers from noisy labeling and long-tail distributions problem. Many advanced approaches usually separately address two problems, which ignore their mutual interactions. In this paper, we propose a novel framework named RH-Net, which utilizes Reinforcement learning and Hierarchical relational searching module to improve relation extraction. We leverage reinforcement learning to instruct the model to select high-quality instances. We then propose the hierarchical relational searching module to share the semantics from correlative instances between data-rich and data-poor classes. During the iterative process, the two modules keep interacting to alleviate the noisy and long-tail problem simultaneously. Extensive experiments on widely used NYT data set clearly show that our method significant improvements over state-of-the-art baselines.

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Denoising iris PCNN+RL+HME Average 84.61 # 1
Relation Extraction NYT PCNN+RL+HME F1 90 # 10


No methods listed for this paper. Add relevant methods here