SeqVAT: Virtual Adversarial Training for Semi-Supervised Sequence Labeling
By Luoxin Chen, Weitong Ruan, Xinyue Liu, Jianhua Lu. 2020
63 citations recorded by the source corpus.
Virtual adversarial training (VAT) is a powerful technique to improve model robustness in both supervised and semi-supervised settings. It is effective and can be easily adopted on lots of image classification and text classification tasks. However, its benefits to sequence labeling tasks such as named entity recognition (NER) have not been shown as significant, mostly, because the previous approach can not combine VAT with the conditional random field (CRF). CRF can significantly boost accuracy for sequence models by putting constraints on label transitions, which makes it an essential component in most state-of-the-art sequence labeling model architectures. In this paper, we propose SeqVAT, a method which naturally applies VAT to sequence labeling models with CRF. Empirical studies show that SeqVAT not only significantly improves the sequence labeling performance over baselines under supervised settings, but also outperforms state-of-the-art approaches under semi-supervised settings.
Subfields: Artificial Intelligence
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
- Mohit Bansal
- Diyi Yang
- Derek Tam
- Colin Raffel
- Jiaao Chen
- Jianfeng Gao
- Ricardo Henao
- Luke S. Zettlemoyer
Citations in the corpus
- Few-Shot Class-Incremental Learning for Named Entity Recognition (2022, background): “However, many current state-of-the-art NER models are built with a CRF module (Liu et al., 2019; Chen et al., 2020; Wang et al., 2021).”
- An Empirical Survey of Data Augmentation for Limited Data Learning in NLP (2021, methodology): “tions (Miyato et al., 2016; Zhu et al., 2019a; Jiang et al., 2019; Chen et al., 2020d) which creates “virtual adversarial examples”.”
- SeqMix: Augmenting Active Sequence Labeling via Sequence Mixup (2020, methodology): “Guo et al. (2019a); Chen et al. (2020a) apply hidden-space Mixup for text classification.”