Adversarial Mask Transformer for Sequential Learning
Authors:
- 23 May 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 27, 4178-4182
Abstract
Mask language model has been successfully developed to build a transformer for robust language understanding. The transformer-based language model has achieved excellent results in various downstream applications. However, typical mask language model is trained by predicting the randomly masked words and is used to transfer the knowledge from rich-resource pre-training task to low-resource downstream tasks. This study incorporates a rich contextual embedding from pre-trained model and strengthens the attention layers for sequence-to-sequence learning. In particular, an adversarial mask mechanism is presented to deal with the shortcoming of random mask and accordingly enhance the robustness in word prediction for language understanding. The adversarial mask language model is trained in accordance with a minimax optimization over the word prediction loss. The worst-case mask is estimated to build an optimal and robust language model. The experiments on two machine translation tasks show the merits of the adversarial mask transformer.Keywords
This publication has 16 references indexed in Scilit:
- Stochastic Adversarial Learning for Domain Adaptation2020
- Variational Domain Adversarial Learning With Mutual Information Maximization for Speaker VerificationIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2020
- Variational Domain Adversarial Learning for Speaker Verification2019
- Variational Bayesian GAN2019
- Mask-Predict: Parallel Decoding of Conditional Masked Language Models2019
- fairseq: A Fast, Extensible Toolkit for Sequence Modeling2019
- Black-Box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers2018
- Understanding Back-Translation at Scale2018
- Findings of the 2017 Conference on Machine Translation (WMT17)2017
- Neural Machine Translation of Rare Words with Subword Units2016