RH-Net: Improving Neural Relation Extraction via Reinforcement Learning and Hierarchical Relational Searching
This work addresses issues in relation extraction for natural language processing, offering an incremental improvement by integrating two modules to handle noise and data imbalance simultaneously.
The paper tackles noisy labeling and long-tail distribution problems in distant supervision for neural relation extraction by proposing RH-Net, which uses reinforcement learning and hierarchical relational searching to improve performance, achieving significant gains over state-of-the-art baselines on the NYT dataset.
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.