Robust Multilingual Part-of-Speech Tagging via Adversarial Training

By Michihiro Yasunaga, Jungo Kasai, Dragomir R. Radev. 2017

109 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Break-It-Fix-It: Unsupervised Learning for Program Repair (2021, methodology): “A common approach is to increase the source side data, for instance by adding modifications or sampling from generative models (Hannun et al., 2014; Jia & Liang, 2016; Krizhevsky et al., 2017; Antoniou et al., 2017; Yasunaga et al., 2018; Yu et al., 2018a; Lee et al., 2019; Berthelot et al., 2019; X”
Adversarial Attacks on Deep Learning Models in Natural Language Processing: A Survey (2019, methodology): “[151] adopted the method in [94] to build a more robust neural network by introducing adversarial training, but they applied the strategy (with minor modifications) in POS tagging.”
SeqVAT: Virtual Adversarial Training for Semi-Supervised Sequence Labeling (2020, methodology): “This approach, named adversarial training (AT), has been reported to be highly effective on image classiﬁcation (Goodfel-low et al., 2015), text classiﬁcation (Miyato et al., 2017), as well as sequence labeling (Yasunaga et al., 2018).”
A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios (2020, background): “They can, however, also be utilized to augment NLP datasets (Yasunaga et al., 2018; Morris et al., 2020).”
Natural Language Processing Advancements By Deep Learning: A Survey (2020, unknown): “55 Adversarial Training + Bi-LSTM [77] 97.”
Neural Unsupervised Domain Adaptation in NLP—A Survey (2020, background): “…to many other tasks as well: language identification (Li et al., 2018a), natural language inference (Rocha and Lopes Cardoso, 2019), POS tagging (Yasunaga et al., 2018), parsing (Sato et al., 2017), trigger identification (Naik and Rose, 2020), relation extraction (Wu et al., 2017; Fu et al.,…”