Papers with masking strategies

12 papers
“Is Whole Word Masking Always Better for Chinese BERT?”: Probing on Chinese Grammatical Error Correction (2022.findings-acl)

Copied to clipboard

Challenge: a Chinese model with whole word masking has no subword because each token is an atomic character.
Approach: They propose to use whole word masking to mask all subwords corresponding to a word at once . they ask models to revise or insert tokens in a masked language modeling manner .
Outcome: The proposed model performs better when one character is inserted or replaced . the model trained with standard character-level masking performs best when one token is masked .
Choosing What to Mask: More Informed Masking for Multimodal Machine Translation (2023.acl-srw)

Copied to clipboard

Challenge: Pre-trained language models have achieved remarkable results on several NLP tasks.
Approach: They propose three new masking strategies for cross-lingual visual pre-training that focus on learning different linguistic patterns.
Outcome: The proposed methods outperform the baseline model and achieve state-of-the-art accuracy on the Portuguese-English MMT task.
On the Robustness of Reading Comprehension Models to Entity Renaming (2022.naacl-main)

Copied to clipboard

Challenge: SpanBERT model is more robust than RoBERTa, despite having similar accuracy on unperturbed test data.
Approach: They propose a pipeline to replace entity names with names from a variety of sources.
Outcome: The proposed model performs worse when entities are renamed, the authors show . SpanBERT, which is pretrained with span-level masking, is more robust than RoBERTa .
Learning Rich Representation of Keyphrases from Text (2022.findings-naacl)

Copied to clipboard

Challenge: Prior work has referred to extractive (part of document) or abstractive (not part of document).
Approach: They propose to use a new pre-training objective to introduce keyphrases into transformer language models in discriminative and generative settings.
Outcome: The proposed model improves performance in discriminative and generative settings and also improves on named entity recognition, question answering, relation extraction and abstractive summarization tasks.
Should You Mask 15% in Masked Language Modeling? (2023.eacl-main)

Copied to clipboard

Challenge: Masked language models (MLMs) traditionally mask 15% of tokens due to the belief that more masking would leave insufficient context to learn good representations.
Approach: They revisit the 15% masking rate of MLMs to examine the role of masking in linguistic training.
Outcome: The proposed masking rate outperforms BERT-large size models on GLUE and SQUAD while maintaining 95% accuracy.
Self-Evolution Learning for Discriminative Language Model Pretraining (2023.findings-acl)

Copied to clipboard

Challenge: Random masking does not consider the importance of the different words in the sentence meaning, e.g., entity-level masking requires expensive prior knowledge and generally does not use existing model weights.
Approach: They propose a token masking and learning method that uses a random masking strategy to learn the under-explored tokens.
Outcome: The proposed method improves linguistic knowledge learning and generalization on 10 tasks.
Data Efficient Masked Language Modeling for Vision and Language (2021.findings-emnlp)

Copied to clipboard

Challenge: Masked language modeling (MLM) is one of the key sub-tasks in vision-language pretraining.
Approach: They propose a masking strategy that masks tokens with a 15% probability for text-only data.
Outcome: The proposed masking strategy outperforms the baseline model on a prompt-based probing task designed to elicit image objects.
KIA: Knowledge-Guided Implicit Vision-Language Alignment for Chest X-Ray Report Generation (2025.coling-main)

Copied to clipboard

Challenge: Existing reports on medical images and reports lack fine-grained cross-modal interaction, leading to insufficient understanding of detailed information.
Approach: They propose a framework for establishing cross-modal semantic alignment in radiology report pairs using knowledge-guided implicit vision-language alignment.
Outcome: KIA improves understanding of medical images and reports by incorporating medical knowledge to enhance pathological observation and anatomical landm.
Improving Pre-trained Language Model Sensitivity via Mask Specific losses: A case study on Biomedical NER (2024.naacl-long)

Copied to clipboard

Challenge: Fine-tuning is the prevailing practice for adapting language models (LMs) to new domains.
Approach: They propose a mask specific language model that weights the importance of domain-specific terms during fine-tuning to avoid insensitivity.
Outcome: The proposed approach outperforms advanced masking strategies such as span- and PMI-based masking.
InforMask: Unsupervised Informative Masking for Language Model Pretraining (2022.emnlp-main)

Copied to clipboard

Challenge: Masked language modeling is used for pretraining large language models for knowledge-intensive tasks.
Approach: They propose an unsupervised masking strategy that exploits Pointwise Mutual Information to select the most informative tokens to mask.
Outcome: The proposed strategy outperforms random masking and previously proposed masking strategies on the factual recall benchmark LAMA and the question answering benchmark SQuAD v1 and v2.
Effective Unsupervised Domain Adaptation with Adversarially Trained Language Models (2020.emnlp-main)

Copied to clipboard

Challenge: Recent work has shown the importance of training contextualised word embedding models on the domain of the target task of interest.
Approach: They propose a masking strategy which adversarially masks out those tokens which are harder to reconstruct by the underlying MLM.
Outcome: The proposed training strategy outperforms random masking on six unsupervised domain adaptation tasks and achieves up to +1.64 F1 score improvements.
LayoutMask: Enhance Text-Layout Interaction in Multi-modal Pre-training for Document Understanding (2023.acl-long)

Copied to clipboard

Challenge: Pre-trained models on document images with transformer-based backbones have led to significant performance gains in this field.
Approach: They propose a multi-modal pre-training model that combines text, layout and image . they propose to use local 1D position instead of global 1D positions as layout input .
Outcome: The proposed model can achieve state-of-the-art results on a wide variety of VrDU problems.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations