# Active Sentence Learning by Adversarial Uncertainty Sampling in Discrete Space

arXiv: https://arxiv.org/abs/2004.08046 · HTML: https://mlsanity.com/paper/2004.08046/

## Key facts

- Cited by 17 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 17 Apr 2020.

## Built on by (most cited first, 17 of 17)

- [Active Learning by Acquiring Contrastive Examples](https://mlsanity.com/paper/2109.03764/) (2021)
- [Uncertainty in Natural Language Processing: Sources, Quantification, and Applications](https://mlsanity.com/paper/2306.04459/) (2023)
- [A Survey of Active Learning for Natural Language Processing](https://mlsanity.com/paper/2210.10109/) (2022)
- [ALLSH: Active Learning Guided by Local Sensitivity and Hardness](https://mlsanity.com/paper/2205.04980/) (2022)
- [Cold-Start Data Selection for Few-shot Language Model Fine-tuning: A Prompt-Based Uncertainty Propagation Approach](https://mlsanity.com/paper/2209.06995/) (2022)
- [ActiveGLAE: A Benchmark for Deep Active Learning with Transformers](https://mlsanity.com/paper/2306.10087/) (2023)
- [FreeAL: Towards Human-Free Active Learning in the Era of Large Language Models](https://mlsanity.com/paper/2311.15614/) (2023)
- [Identifying Adversarially Attackable and Robust Samples](https://mlsanity.com/paper/2301.12896/) (2023)
- [A Proxy Attack-Free Strategy for Practically Improving the Poisoning Efficiency in Backdoor Attacks](https://mlsanity.com/paper/2306.08313/) (2023)
- [Multi-Stage Balanced Distillation: Addressing Long-Tail Challenges in Sequence-Level Knowledge Distillation](https://mlsanity.com/paper/2406.13114/) (2024)
- [Multi-View Active Learning for Short Text Classification in User-Generated Data](https://mlsanity.com/paper/2112.02611/) (2021)
- [REAL: A Representative Error-Driven Approach for Active Learning](https://mlsanity.com/paper/2307.00968/) (2023)
- [Divide & Conquer for Entailment-aware Multi-hop Evidence Retrieval](https://mlsanity.com/paper/2311.02616/) (2023)
- [AcTune: Uncertainty-aware Active Self-Training for Semi-Supervised Active Learning with Pretrained Language Models](https://mlsanity.com/paper/2112.08787/) (2021)
- [Perturbation-based Active Learning for Question Answering](https://mlsanity.com/paper/2311.02345/) (2023)
- [ALVIN: Active Learning Via INterpolation](https://mlsanity.com/paper/2410.08972/) (2024)
- [Generalized Category Discovery in Event-Centric Contexts: Latent Pattern Mining with LLMs](https://mlsanity.com/paper/2505.23304/) (2025)

## Abstract (arXiv)

Active learning for sentence understanding aims at discovering informative unlabeled data for annotation and therefore reducing the demand for labeled data. We argue that the typical uncertainty sampling method for active learning is time-consuming and can hardly work in real-time, which may lead to ineffective sample selection. We propose adversarial uncertainty sampling in discrete space (AUSDS) to retrieve informative unlabeled samples more efficiently. AUSDS maps sentences into latent space generated by the popular pre-trained language models, and discover informative unlabeled text samples for annotation via adversarial attack. The proposed approach is extremely efficient compared with traditional uncertainty sampling with more than 10x speedup. Experimental results on five datasets show that AUSDS outperforms strong baselines on effectiveness.