Papers › Robust Multilingual Part-of-Speech Tagging via Adversarial Training
Robust Multilingual Part-of-Speech Tagging via Adversarial Training
Michihiro Yasunaga, Jungo Kasai, Dragomir Radev
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.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Chunking | CoNLL 2000 | Adversarial Training | Exact Span F1 | 95.25 | #8 of 9 | Archive leaderboard | report |
| Chunking | CoNLL 2000 | BiLSTM-CRF | Exact Span F1 | 95.18 | #9 of 9 | Archive leaderboard | report |
| Named Entity Recognition (NER) | CoNLL 2003 (English) | Adversarial Bi-LSTM | F1 | 91.56 | #61 of 73 | Archive leaderboard | report |
| Part-Of-Speech Tagging | Penn Treebank | Adversarial Bi-LSTM | Accuracy | 97.59 | #8 of 20 | Archive leaderboard | report |
| Part-Of-Speech Tagging | UD | Adversarial Bi-LSTM | Avg accuracy | 96.65 | #2 of 5 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections