Reinforced Co-Training (N18-1)

Copied to clipboard

Challenge: Existing co-training methods ignore sampling bias and fail to explore the data space.
Approach: They propose a method to select high-quality unlabeled samples to better co-train on by learning a selection policy with a small labeled dataset.
Outcome: The proposed method can obtain more accurate text classification results on clickbait detection and generic text classification tasks.

Similar Papers

Zero-shot Text Classification via Reinforced Self-training (2020.acl-main)

Copied to clipboard

Challenge: Existing methods to learn from unlabeled data are difficult for zero-shot text classification tasks.
Approach: They propose a self-training based method to efficiently leverage unlabeled data.
Outcome: The proposed method significantly outperforms existing methods in zero-shot text classification tasks on benchmarks and a real-world e-commerce dataset.
Reinforced Active Learning for Low-Resource, Domain-Specific, Multi-Label Text Classification (2023.findings-acl)

Copied to clipboard

Challenge: Modern text classification systems achieve excellent accuracy across tasks and corpora.
Approach: They propose a Reinforcement Learning policy that uses many different aspects of the data and task to select the most informative unlabeled subset dynamically over the course of the AL procedure.
Outcome: The proposed framework outperforms baselines on four complex multi-class, multi-label text classification datasets.
LLM-Guided Co-Training for Text Classification (2025.emnlp-main)

Copied to clipboard

Challenge: Empirical results show that it achieves state-of-the-art performance on 4 out of 5 benchmark datasets and ranks first among 14 compared methods according to the Friedman test.
Approach: They propose a weighted co-training approach that is guided by Large Language Models (LLMs) they use LLM labels on unlabeled data as target labels and co-train two encoder-only based networks that train each other over multiple iterations.
Outcome: The proposed approach outperforms conventional methods on 4 out of 5 benchmark datasets and ranks first among 14 compared methods according to the Friedman test.
A Deep Reinforced Sequence-to-Set Model for Multi-Label Classification (P19-1)

Copied to clipboard

Challenge: Multi-label classification (MLC) aims to assign multiple labels to each sample.
Approach: They propose a sequence-to-set model that is trained via reinforcement learning and rewards feedback independent of the label order.
Outcome: The proposed model outperforms baseline models and reduces sensitivity to label order.
CoAug: Combining Augmentation of Labels and Labelling Rules (2023.findings-acl)

Copied to clipboard

Challenge: Named Entity Recognition (NER) tasks require large labeled datasets to perform well.
Approach: They propose a co-augmentation framework that bootstraps predictions from each model to improve few-shot models and rule-augmentation models by bootstrapping them.
Outcome: The proposed model outperforms strong weak-supervision-based models by 6.5 F1 points . the proposed model can learn from limited labeled data and perform better on small datasets .
Reinforced Training Data Selection for Domain Adaptation (P19-1)

Copied to clipboard

Challenge: Existing approaches to learn domains with massive data are not easy to implement and require a predefined threshold.
Approach: They propose a framework that searches for training instances relevant to the target domain and learns better representations for them.
Outcome: The proposed framework is effective in data selection and representation, but generalized to accommodate different NLP tasks.
Leveraging Training Dynamics and Self-Training for Text Classification (2022.findings-emnlp)

Copied to clipboard

Challenge: Semi-supervised learning (SSL) is a promising technique for improving deep learning models when training data is scarce.
Approach: They propose a semi-supervised learning approach that leverages training dynamics of unlabeled data.
Outcome: The proposed method achieves an average increase in F1 score of 3.5% over baselines in low resource settings.
Efficient (Soft) Q-Learning for Text Generation with Limited Good Data (2022.findings-emnlp)

Copied to clipboard

Challenge: Maximum likelihood estimation (MLE) is the predominant method for training text generation models.
Approach: They propose a new RL formulation for text generation from the soft Q-learning perspective using path consistency learning to combine the best of on-/off-policy updates and learn effectively from sparse reward.
Outcome: The proposed approach outperforms MLE and previous RL methods in a wide range of tasks.
Learning to Learn and Predict: A Meta-Learning Approach for Multi-Label Classification (D19-1)

Copied to clipboard

Challenge: Existing models for multi-label classification ignore complexity and dependencies among labels . Experimental results show that our method can obtain more accurate multi-lab classification results.
Approach: They propose a meta-learning method to capture complex label dependencies . they use a Meta-learner to jointly learn the training policies and prediction policies for different labels.
Outcome: The proposed method can capture complex label dependencies on fine-grained entity typing and text classification tasks.
Delta-training: Simple Semi-Supervised Text Classification using Pretrained Word Embeddings (D19-1)

Copied to clipboard

Challenge: Pretrained word embeddings outperforms classifiers with randomly initialized word embeds, a new method is proposed for semi-supervised text classification.
Approach: They propose a method that uses pretrained word embeddings to predict text classification . they use unlabeled data to build a classifier, and use early-stopping to improve performance .
Outcome: The proposed method outperforms self-training and co-training frameworks on unlabeled data.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations