Papers › Neural Mask Generator: Learning to Generate Adaptive Word Maskings for Language Model...

Neural Mask Generator: Learning to Generate Adaptive Word Maskings for Language Model Adaptation

6 Oct 2020EMNLP 2020 11arXiv:2010.02705archive 2025-07-28

Minki Kang, Moonsu Han, Sung Ju Hwang

We propose a method to automatically generate a domain- and task-adaptive maskings of the given text for self-supervised pre-training, such that we can effectively adapt the language model to a particular target task (e.g. question answering). Specifically, we present a novel reinforcement learning-based framework which learns the masking policy, such that using the generated masks for further pre-training of the target language model helps improve task performance on unseen texts. We use off-policy actor-critic with entropy regularization and experience replay for reinforcement learning, and propose a Transformer-based policy network that can consider the relative importance of words in a given text. We validate our Neural Mask Generator (NMG) on several question answering and text classification datasets using BERT and DistilBERT as the language models, on which it outperforms rule-based masking strategies, by automatically learning optimal adaptive maskings.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

Nardien/NMG officialmentioned in paperpytorch report

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

Language ModelingLanguage ModellingQuestion AnsweringReinforcement LearningReinforcement Learning (RL)Text Classificationreinforcement-learningtext-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamAttentionAttention DropoutBERTDense ConnectionsDistilBERTDropoutEntropy RegularizationExperience ReplayLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSoftmaxWeight DecayWordPiece

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