Robust Multilingual Part-of-Speech Tagging via Adversarial Training

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... (read more)

PDF Abstract NAACL 2018 PDF NAACL 2018 Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Chunking CoNLL 2000 Adversarial Training Exact Span F1 95.25 # 6
Chunking CoNLL 2000 BiLSTM-CRF Exact Span F1 95.18 # 7
Named Entity Recognition CoNLL 2003 (English) Adversarial Bi-LSTM F1 91.56 # 34
Part-Of-Speech Tagging Penn Treebank Adversarial Bi-LSTM Accuracy 97.59 # 7
Part-Of-Speech Tagging UD Adversarial Bi-LSTM Avg accuracy 96.73 # 2

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet