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.

Similar Papers

Masking as an Efficient Alternative to Finetuning for Pretrained Language Models (2020.emnlp-main)

Copied to clipboard

Challenge: Extensive evaluations of masking BERT, RoBERTa, and DistilBERT on eleven diverse NLP tasks show that our binary masked language models encode information necessary for solving downstream tasks.
Approach: They propose an efficient method of utilizing pretrained language models where selective binary masks are learned instead of finetuning.
Outcome: Extensive evaluations of masking BERT, RoBERTa, and DistilBERT on eleven diverse NLP tasks show that the proposed method yields comparable performance to finetuning, but has a much smaller memory footprint when multiple tasks need to be solved.
Mask More and Mask Later: Efficient Pre-training of Masked Language Models by Disentangling the [MASK] Token (2022.findings-emnlp)

Copied to clipboard

Challenge: Large-scale pre-trained MLMs can be used to generalize well to a wide range of tasks.
Approach: They propose to append [MASK]s at a later layer to reduce sequence length for earlier layers.
Outcome: The proposed method outperforms RoBERTa for 6 out of 8 GLUE tasks on average by 0.4%.
Unsupervised Improvement of Factual Knowledge in Language Models (2023.eacl-main)

Copied to clipboard

Challenge: Masked language modeling (MLM) is often dominated by high-frequency words that are sub-optimal for learning factual knowledge.
Approach: They propose an approach that forces the model to prioritize informative words in a fully unsupervised way.
Outcome: The proposed approach significantly improves the performance of pretrained language models on factual recall, question answering, sentiment analysis, and natural language inference in a closed-book setting.
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.
Frustratingly Simple Pretraining Alternatives to Masked Language Modeling (2021.emnlp-main)

Copied to clipboard

Challenge: Masked language modeling (MLM) is widely used in natural language processing for self-supervised learning of text representations.
Approach: They propose to use token-level classification tasks as main pretraining objectives instead of Masked language modeling (MLM) . Empirical results show that pretraining a model with 41% of the BERT-BASE’s parameters, BERT MEDIUM results in only a 1% drop in GLUE scores with their best objective.
Outcome: Empirical results show that the proposed methods achieve comparable or better performance to MLM using a BERT-BASE architecture.
Train No Evil: Selective Masking for Task-Guided Pre-Training (2020.emnlp-main)

Copied to clipboard

Challenge: Pre-trained language models can't capture domain-specific and task-specific patterns because of the task-agnostic pre-training stage.
Approach: They propose a task-guided pre-training stage with selective masking between general pre-train and fine-tuning to learn domain-specific patterns.
Outcome: The proposed method can achieve comparable or even better performance with less than 50% of computation cost.
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.
Masked Latent Semantic Modeling: an Efficient Pre-training Alternative to Masked Language Modeling (2023.findings-acl)

Copied to clipboard

Challenge: a recent study suggests that masked language models are a useful pre-training technique for natural language processing . a study using mlms pre-trained by a team of researchers has improved performance .
Approach: They propose an alternative to the classic masked language modeling paradigm . they use an unsupervised technique which uses sparse coding to make the prediction possible .
Outcome: The proposed technique improves on pre-trained models compared to vanilla MLM . the proposed model returns distributions over their vocabulary peaking at plausible substitutes .
Neural Mask Generator: Learning to Generate Adaptive Word Maskings for Language Model Adaptation (2020.emnlp-main)

Copied to clipboard

Challenge: Existing methods to train language models on diverse text corpora have brought up performance improvements on several natural language understanding (NLU) tasks.
Approach: They propose a method to automatically generate domain- and task-adaptive maskings of a given text for self-supervised pre-training.
Outcome: The proposed framework outperforms rule-based masking strategies on question answering and text classification datasets on which it outperformed rule-driven masking techniques.
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.

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