mlsanityData to 14 Oct 2026

Gradient Imitation Reinforcement Learning for General Low-Resource Information Extraction

arXiv 2211.06014 ↗First posted 11 Nov 2022cs.CL cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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).

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 47 of its 82 references that are in the map. First posted on arXiv 11 Nov 2022.

Builds on

47 of 82 references.

References · 47

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  3. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  4. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  5. 2017Decoupled Weight Decay Regularizationcited by 1,831
  6. 2016Understanding deep learning requires rethinking generalizationcited by 1,674
  7. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,391
  8. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,311
  9. 2020Gradient Surgery for Multi-Task Learningcited by 1,256
  10. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,060
  11. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 788
  12. 2021FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labelingcited by 540
35 more
  1. 2016Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learningcited by 441
  2. 2016Adversarial Feature Learningcited by 350
  3. 2016Deep Reinforcement Learning for Dialogue Generationcited by 288
  4. 2019Matching the Blanks: Distributional Similarity for Relation Learningcited by 272
  5. 2019Entity, Relation, and Event Extraction with Contextualized Span Representationscited by 262
  6. 2021A Survey on Deep Semi-supervised Learningcited by 251
  7. 2021Text2Event: Controllable Sequence-to-Structure Generation for End-to-end Event Extractioncited by 129
  8. 2018Achieving Human Parity on Automatic Chinese to English News Translationcited by 119
  9. 2020Towards Deeper Graph Neural Networks with Differentiable Group Normalizationcited by 114
  10. 2019Dual Student: Breaking the Limits of the Teacher in Semi-supervised Learningcited by 104
  11. 2018Adapting Auxiliary Losses Using Gradient Similaritycited by 100
  12. 2019Neural Machine Translation: A Review and Surveycited by 100
  13. 2015Deep Reinforcement Learning with a Natural Language Action Spacecited by 88
  14. 2017Good Semi-supervised Learning that Requires a Bad GANcited by 86
  15. 2019SemEval-2010 Task 8: Multi-Way Classification of Semantic Relations Between Pairs of Nominalscited by 63
  16. 2017Paraphrase Generation with Deep Reinforcement Learningcited by 58
  17. 2018Improving the Improved Training of Wasserstein GANs: A Consistency Term and Its Dual Effectcited by 49
  18. 2018A Hierarchical Framework for Relation Extraction with Reinforcement Learningcited by 49
  19. 2020SelfORE: Self-supervised Relational Feature Learning for Open Relation Extractioncited by 43
  20. 2018Deep Reinforcement Learning For Sequence to Sequence Modelscited by 39
  21. 2020Semi-supervised Relation Extraction via Incremental Meta Self-Trainingcited by 35
  22. 2021Gradient Imitation Reinforcement Learning for Low Resource Relation Extractioncited by 33
  23. 2022HiURE: Hierarchical Exemplar Contrastive Learning for Unsupervised Relation Extractioncited by 32
  24. 2021Survey on reinforcement learning for language processingcited by 31
  25. 2019Semantic Parsing with Dual Learningcited by 28
  26. 2021Noisy-Labeled NER with Confidence Estimationcited by 28
  27. 2016Semi-Supervised Learning with Context-Conditional Generative Adversarial Networkscited by 19
  28. 2016Improving Information Extraction by Acquiring External Evidence with Reinforcement Learningcited by 16
  29. 2019Learning Dual Retrieval Module for Semi-supervised Relation Extractioncited by 12
  30. 2021Deep Neural Network Based Relation Extraction: An Overviewcited by 11
  31. 2019Interactive-Predictive Neural Machine Translation through Reinforcement and Imitationcited by 7
  32. 2020Dual Learning for Semi-Supervised Natural Language Understandingcited by 7
  33. 2017Tackling Error Propagation through Reinforcement Learning: A Case of Greedy Dependency Parsingcited by 4
  34. 2022Asking the Right Questions in Low Resource Template Extractioncited by 4
  35. 2020Exploit Multiple Reference Graphs for Semi-supervised Relation Extractioncited by 2

Built on by

Not cited yet.