English
Related papers

Related papers: Token Dropping for Efficient BERT Pretraining

200 papers

Pre-trained transformer models shine in many natural language processing tasks and therefore are expected to bear the representation of the input sentence or text meaning. These sentence-level embeddings are also important in…

Computation and Language · Computer Science 2025-02-21 Lukas Stankevičius , Mantas Lukoševičius

Recently, pre-trained contextual models, such as BERT, have shown to perform well in language related tasks. We revisit the design decisions that govern the applicability of these models for the passage re-ranking task in open-domain…

Information Retrieval · Computer Science 2021-08-31 Jurek Leonhardt , Fabian Beringer , Avishek Anand

In Transformer architectures, tokens\textemdash discrete units derived from raw data\textemdash are formed by segmenting inputs into fixed-length chunks. Each token is then mapped to an embedding, enabling parallel attention computations…

Machine Learning · Computer Science 2026-01-14 Zhenglun Kong , Yize Li , Fanhu Zeng , Lei Xin , Shvat Messica , Xue Lin , Pu Zhao , Manolis Kellis , Hao Tang , Marinka Zitnik

How does language model pretraining help transfer learning? We consider a simple ablation technique for determining the impact of each pretrained layer on transfer task performance. This method, partial reinitialization, involves replacing…

Computation and Language · Computer Science 2020-11-11 Alex Tamkin , Trisha Singh , Davide Giovanardi , Noah Goodman

Masked language modeling has become a standard pretraining objective for training encoder-based language models. In this approach, certain tokens in the input are masked, and the model learns to predict them using the surrounding context.…

Artificial Intelligence · Computer Science 2026-05-28 Gokul Srinivasagan , Kai Hartung , Munir Georges

Transformer-based masked language models such as BERT, trained on general corpora, have shown impressive performance on downstream tasks. It has also been demonstrated that the downstream task performance of such models can be improved by…

Computation and Language · Computer Science 2023-05-04 Zhi Hong , Aswathy Ajith , Gregory Pauloski , Eamon Duede , Kyle Chard , Ian Foster

Pre-trained language models in the past years have shown exponential growth in model parameters and compute time. ELECTRA is a novel approach for improving the compute efficiency of pre-trained language models (e.g. BERT) based on masked…

Computation and Language · Computer Science 2021-10-14 Junmo Kang , Suwon Shin , Jeonghwan Kim , Jaeyoung Jo , Sung-Hyon Myaeng

Diffusion language models generate text through iterative refinement, a process that is often computationally inefficient because many tokens reach stability long before the final denoising step. We introduce a training-free, token-level…

Machine Learning · Computer Science 2026-02-12 Zahar Kohut , Severyn Shykula , Dmytro Khamula , Mykola Vysotskyi , Taras Rumezhak , Volodymyr Karpiv

With the growing burden of training deep learning models with large data sets, transfer-learning has been widely adopted in many emerging deep learning algorithms. Transformer models such as BERT are the main player in natural language…

Cryptography and Security · Computer Science 2022-07-21 Mujahid Al Rafi , Yuan Feng , Hyeran Jeon

Recently, leveraging pre-trained Transformer based language models in down stream, task specific models has advanced state of the art results in natural language understanding tasks. However, only a little research has explored the…

Computation and Language · Computer Science 2020-12-07 Daniel Grießhaber , Johannes Maucher , Ngoc Thang Vu

As Transfer Learning from large-scale pre-trained models becomes more prevalent in Natural Language Processing (NLP), operating these large models in on-the-edge and/or under constrained computational training or inference budgets remains…

Computation and Language · Computer Science 2020-03-03 Victor Sanh , Lysandre Debut , Julien Chaumond , Thomas Wolf

While modern Transformer-based language models (LMs) have achieved major success in multi-task generalization, they often struggle to capture long-range dependencies within their context window. This work introduces a novel approach using…

Computation and Language · Computer Science 2025-09-23 Alok N. Shah , Khush Gupta , Keshav Ramji , Pratik Chaudhari

Transformer-based pre-trained models with millions of parameters require large storage. Recent approaches tackle this shortcoming by training adapters, but these approaches still require a relatively large number of parameters. In this…

Computation and Language · Computer Science 2023-01-31 Chin-Lun Fu , Zih-Ching Chen , Yun-Ru Lee , Hung-yi Lee

Resource limitations often constrain the parameter counts of Large Language Models (LLMs), hindering their performance. While existing methods employ parameter sharing to reuse the same parameter set under fixed budgets, such approaches…

Computation and Language · Computer Science 2025-02-19 Guanghao Li , Wenhao Jiang , Li Shen , Ming Tang , Chun Yuan

As large language models (LLMs) become increasingly powerful, the sequential nature of autoregressive generation creates a fundamental throughput bottleneck that limits the practical deployment. While Multi-Token Prediction (MTP) has…

Machine Learning · Computer Science 2025-09-24 Yuxuan Cai , Xiaozhuan Liang , Xinghua Wang , Jin Ma , Haijin Liang , Jinwen Luo , Xinyu Zuo , Lisheng Duan , Yuyang Yin , Xi Chen

Contextual embedding-based language models trained on large data sets, such as BERT and RoBERTa, provide strong performance across a wide range of tasks and are ubiquitous in modern NLP. It has been observed that fine-tuning these models on…

Computation and Language · Computer Science 2021-09-16 Vin Sachidananda , Jason S. Kessler , Yi-an Lai

The computational cost of training multimodal large language models (MLLMs) grows rapidly with the number of processed tokens. Existing efficiency methods mainly target inference via token reduction or merging, offering limited benefits…

Computer Vision and Pattern Recognition · Computer Science 2026-04-30 Chaoyu Li , Yogesh Kulkarni , Pooyan Fazli

Massively pre-trained transformer models are computationally expensive to fine-tune, slow for inference, and have large storage requirements. Recent approaches tackle these shortcomings by training smaller models, dynamically reducing the…

Machine Learning · Computer Science 2021-10-07 Andreas Rücklé , Gregor Geigle , Max Glockner , Tilman Beck , Jonas Pfeiffer , Nils Reimers , Iryna Gurevych

Embedding layers in transformer-based NLP models typically account for the largest share of model parameters, scaling with vocabulary size but not yielding performance gains proportional to scale. We propose an alternative approach in which…

Computation and Language · Computer Science 2025-05-06 Henry Ndubuaku , Mouad Talhi

Masked language modeling (MLM) pre-training models such as BERT corrupt the input by replacing some tokens with [MASK] and then train a model to reconstruct the original tokens. This is an effective technique which has led to good results…

Computation and Language · Computer Science 2020-06-11 Andy Wagner , Tiyasa Mitra , Mrinal Iyer , Godfrey Da Costa , Marc Tremblay