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

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

URL: http://arxiv.org/abs/2010.14255v2
Date: Tue, 2 Feb 2021 07:24:01 GMT
Title: RH-Net: Improving Neural Relation Extraction via Reinforcement Learning and Hierarchical Relational Searching
Authors: Jianing Wang
Abstract summary: We propose a novel framework named RH-Net, which utilizes Reinforcement learning and Hierarchical relational searching module to improve relation extraction. We then propose the hierarchical relational searching module to share the semantics from correlative instances between data-rich and data-poor classes.
Score: 2.1828601975620257
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: 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.