# Robust Multilingual Part-of-Speech Tagging via Adversarial Training

arXiv: https://arxiv.org/abs/1711.04903 · HTML: https://mlsanity.com/paper/1711.04903/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Nov 2017.

## Built on by (most cited first, 21 of 21)

- [Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Training](https://mlsanity.com/paper/2405.20978/) (2024)
- [Break-It-Fix-It: Unsupervised Learning for Program Repair](https://mlsanity.com/paper/2106.06600/) (2021)
- [e-CARE: a New Dataset for Exploring Explainable Causal Reasoning](https://mlsanity.com/paper/2205.05849/) (2022)
- [Enhancing Knowledge Tracing via Adversarial Training](https://mlsanity.com/paper/2108.04430/) (2021)
- [Pushing the Limits of ChatGPT on NLP Tasks](https://mlsanity.com/paper/2306.09719/) (2023)
- [A Survey of Adversarial Defences and Robustness in NLP](https://mlsanity.com/paper/2203.06414/) (2022)
- [Conformal prediction for text infilling and part-of-speech prediction](https://mlsanity.com/paper/2111.02592/) (2021)
- [Zero-shot Transfer of Article-aware Legal Outcome Classification for European Court of Human Rights Cases](https://mlsanity.com/paper/2302.00609/) (2023)
- [Bridging the Gap Between Clean Data Training and Real-World Inference for Spoken Language Understanding](https://mlsanity.com/paper/2104.06393/) (2021)
- [Making Attention Mechanisms More Robust and Interpretable with Virtual Adversarial Training](https://mlsanity.com/paper/2104.08763/) (2021)
- [GradSim: Gradient-Based Language Grouping for Effective Multilingual Training](https://mlsanity.com/paper/2310.15269/) (2023)
- [Robust Learning for Text Classification with Multi-source Noise Simulation and Hard Example Mining](https://mlsanity.com/paper/2107.07113/) (2021)
- [How Does Adversarial Fine-Tuning Benefit BERT?](https://mlsanity.com/paper/2108.13602/) (2021)
- [Optimal Size-Performance Tradeoffs: Weighing PoS Tagger Models](https://mlsanity.com/paper/2104.07951/) (2021)
- [Cross-Lingual Transfer Learning for Statistical Type Inference](https://mlsanity.com/paper/2107.00157/) (2021)
- [Generative Adversarial Training Can Improve Neural Language Models](https://mlsanity.com/paper/2211.09728/) (2022)
- [Open Information Extraction via Chunks](https://mlsanity.com/paper/2305.03299/) (2023)
- [Beyond Hard Samples: Robust and Effective Grammatical Error Correction with Cycle Self-Augmenting](https://mlsanity.com/paper/2310.13321/) (2023)
- [Adversarial Training for Machine Reading Comprehension with Virtual Embeddings](https://mlsanity.com/paper/2106.04437/) (2021)
- [GWPT: A Green Word-Embedding-based POS Tagger](https://mlsanity.com/paper/2401.07475/) (2024)
- [Fake News Classification in Urdu: A Domain Adaptation Approach for a Low-Resource Language](https://mlsanity.com/paper/2512.22778/) (2025)

## Abstract (arXiv)

Adversarial training (AT) is a powerful regularization method for neural networks, aiming to achieve robustness to input perturbations. Yet, the specific effects of the robustness obtained from AT are still unclear in the context of natural language processing. In this paper, we propose and analyze a neural POS tagging model that exploits AT. In our experiments on the Penn Treebank WSJ corpus and the Universal Dependencies (UD) dataset (27 languages), we find that AT not only improves the overall tagging accuracy, but also 1) prevents over-fitting well in low resource languages and 2) boosts tagging accuracy for rare / unseen words. We also demonstrate that 3) the improved tagging performance by AT contributes to the downstream task of dependency parsing, and that 4) AT helps the model to learn cleaner word representations. 5) The proposed AT model is generally effective in different sequence labeling tasks. These positive results motivate further use of AT for natural language tasks.