English

Gradient Imitation Reinforcement Learning for General Low-Resource Information Extraction

Computation and Language 2022-11-15 v2 Artificial Intelligence

Abstract

Information Extraction (IE) aims to extract structured information from heterogeneous sources. IE from natural language texts include sub-tasks such as Named Entity Recognition (NER), Relation Extraction (RE), and Event Extraction (EE). Most IE systems require comprehensive understandings of sentence structure, implied semantics, and domain knowledge to perform well; thus, IE tasks always need adequate external resources and annotations. However, it takes time and effort to obtain more human annotations. Low-Resource Information Extraction (LRIE) strives to use unsupervised data, reducing the required resources and human annotation. In practice, existing systems either utilize self-training schemes to generate pseudo labels that will cause the gradual drift problem, or leverage consistency regularization methods which inevitably possess confirmation bias. To alleviate confirmation bias due to the lack of feedback loops in existing LRIE learning paradigms, we develop a Gradient Imitation Reinforcement Learning (GIRL) method to encourage pseudo-labeled data to imitate the gradient descent direction on labeled data, which can force pseudo-labeled data to achieve better optimization capabilities similar to labeled data. Based on how well the pseudo-labeled data imitates the instructive gradient descent direction obtained from labeled data, we design a reward to quantify the imitation process and bootstrap the optimization capability of pseudo-labeled data through trial and error. In addition to learning paradigms, GIRL is not limited to specific sub-tasks, and we leverage GIRL to solve all IE sub-tasks (named entity recognition, relation extraction, and event extraction) in low-resource settings (semi-supervised IE and few-shot IE).

Keywords

Cite

@article{arxiv.2211.06014,
  title  = {Gradient Imitation Reinforcement Learning for General Low-Resource Information Extraction},
  author = {Xuming Hu and Shiao Meng and Chenwei Zhang and Xiangli Yang and Lijie Wen and Irwin King and Philip S. Yu},
  journal= {arXiv preprint arXiv:2211.06014},
  year   = {2022}
}

Comments

This work has been submitted to the IEEE for possible publication. This work is a substantially extended version of arXiv:2109.06415, with the summary of difference provided in the appendix

R2 v1 2026-06-28T05:39:10.536Z