English
Related papers

Related papers: Weighted Sampling for Masked Language Modeling

200 papers

Recent advancements in language models and pre-trained language models like BERT and RoBERTa have revolutionized natural language processing, enabling a deeper understanding of human-like language. In this paper, we explore enhancing…

Information Retrieval · Computer Science 2025-04-15 Ngoc Luyen Le , Marie-Hélène Abel

Token embeddings in multilingual BERT (m-BERT) contain both language and semantic information. We find that the representation of a language can be obtained by simply averaging the embeddings of the tokens of the language. Given this…

Computation and Language · Computer Science 2021-11-02 Chi-Liang Liu , Tsung-Yuan Hsu , Yung-Sung Chuang , Chung-Yi Li , Hung-yi Lee

Data augmentation is an effective technique for improving the performance of machine learning models. However, it has not been explored as extensively in natural language processing (NLP) as it has in computer vision. In this paper, we…

Computation and Language · Computer Science 2024-01-04 Himmet Toprak Kesgin , Mehmet Fatih Amasyali

We propose a simple method to align multilingual contextual embeddings as a post-pretraining step for improved zero-shot cross-lingual transferability of the pretrained models. Using parallel data, our method aligns embeddings on the word…

Computation and Language · Computer Science 2021-04-13 Lin Pan , Chung-Wei Hang , Haode Qi , Abhishek Shah , Saloni Potdar , Mo Yu

As retrieval-augmented generation prevails in large language models, embedding models are becoming increasingly crucial. Despite the growing number of general embedding models, prior work often overlooks the critical role of training data…

Computation and Language · Computer Science 2025-01-16 Xinshuo Hu , Zifei Shan , Xinping Zhao , Zetian Sun , Zhenyu Liu , Dongfang Li , Shaolin Ye , Xinyuan Wei , Qian Chen , Baotian Hu , Haofen Wang , Jun Yu , Min Zhang

While transformer-based models achieve strong performance on text classification, we explore whether masking input tokens can further enhance their effectiveness. We propose token masking regularization, a simple yet theoretically motivated…

Computation and Language · Computer Science 2025-05-20 Xianglong Xu , John Bowen , Rojin Taheri

We propose PromptBERT, a novel contrastive learning method for learning better sentence representation. We firstly analyze the drawback of current sentence embedding from original BERT and find that it is mainly due to the static token…

Computation and Language · Computer Science 2022-10-14 Ting Jiang , Jian Jiao , Shaohan Huang , Zihan Zhang , Deqing Wang , Fuzhen Zhuang , Furu Wei , Haizhen Huang , Denvy Deng , Qi Zhang

High-dimensional token embeddings underpin Large Language Models (LLMs), as they can capture subtle semantic information and significantly enhance the modelling of complex language patterns. However, this high dimensionality also introduces…

Computation and Language · Computer Science 2024-10-07 Mingxue Xu , Yao Lei Xu , Danilo P. Mandic

Large Language Models (LLMs) require alignment with human preferences to avoid generating offensive, false, or meaningless content. Recently, low-resource methods for LLM alignment have been popular, while still facing challenges in…

Computation and Language · Computer Science 2025-06-10 Feifan Song , Shaohang Wei , Wen Luo , Yuxuan Fan , Tianyu Liu , Guoyin Wang , Houfeng Wang

We introduce Predictive Batch Scheduling (PBS), a novel training optimization technique that accelerates language model convergence by dynamically prioritizing high-loss samples during batch construction. Unlike curriculum learning…

Artificial Intelligence · Computer Science 2026-02-20 Sumedh Rasal

Transfer learning with large pretrained transformer-based language models like BERT has become a dominating approach for most NLP tasks. Simply fine-tuning those large language models on downstream tasks or combining it with task-specific…

Computation and Language · Computer Science 2021-08-06 Wenjuan Han , Bo Pang , Yingnian Wu

Pre-trained language models (PLMs) like BERT are being used for almost all language-related tasks, but interpreting their behavior still remains a significant challenge and many important questions remain largely unanswered. In this work,…

Computation and Language · Computer Science 2021-09-28 Samuel Stevens , Yu Su

While pretrained language models (PLMs) primarily serve as general-purpose text encoders that can be fine-tuned for a wide variety of downstream tasks, recent work has shown that they can also be rewired to produce high-quality word…

Computation and Language · Computer Science 2023-05-30 Tommaso Green , Simone Paolo Ponzetto , Goran Glavaš

Massively multilingual language models such as multilingual BERT offer state-of-the-art cross-lingual transfer performance on a range of NLP tasks. However, due to limited capacity and large differences in pretraining data sizes, there is a…

Computation and Language · Computer Science 2021-09-13 Jonas Pfeiffer , Ivan Vulić , Iryna Gurevych , Sebastian Ruder

The state-of-the-art pre-trained language representation models, such as Bidirectional Encoder Representations from Transformers (BERT), rarely incorporate commonsense knowledge or other knowledge explicitly. We propose a pre-training…

Computation and Language · Computer Science 2020-05-07 Zhi-Xiu Ye , Qian Chen , Wen Wang , Zhen-Hua Ling

Masked Language Modeling (MLM) has been widely used as the denoising objective in pre-training language models (PrLMs). Existing PrLMs commonly adopt a Random-Token Masking strategy where a fixed masking ratio is applied and different…

Computation and Language · Computer Science 2023-05-26 Dongjie Yang , Zhuosheng Zhang , Hai Zhao

Pretrained language models like BERT have achieved good results on NLP tasks, but are impractical on resource-limited devices due to memory footprint. A large fraction of this footprint comes from the input embeddings with large input…

Computation and Language · Computer Science 2021-02-09 Sanqiang Zhao , Raghav Gupta , Yang Song , Denny Zhou

Language models (LMs) are bound to their tokenizer, which maps raw text to a sequence of vocabulary items (tokens). This restricts their flexibility: for example, LMs trained primarily on English may still perform well in other natural and…

Computation and Language · Computer Science 2025-10-29 Benjamin Minixhofer , Edoardo Maria Ponti , Ivan Vulić

The exponential growth of online textual content across diverse domains has necessitated advanced methods for automated text classification. Large Language Models (LLMs) based on transformer architectures have shown significant success in…

Computation and Language · Computer Science 2025-09-09 Zhyar Rzgar K Rostam , Gábor Kertész

We introduce a simple modification to the embedding layer. The key change is to infuse token embeddings with information about their spelling. Models trained with these embeddings improve not only on spelling, but also across standard…

Machine Learning · Computer Science 2026-01-27 Markus N. Rabe , Judith Clymo , Zheren Dong