English
Related papers

Related papers: Q-BERT: Hessian Based Ultra Low Precision Quantiza…

200 papers

Natural Language Processing (NLP) has recently achieved great success by using huge pre-trained models with hundreds of millions of parameters. However, these models suffer from heavy model sizes and high latency such that they cannot be…

Computation and Language · Computer Science 2020-04-16 Zhiqing Sun , Hongkun Yu , Xiaodan Song , Renjie Liu , Yiming Yang , Denny Zhou

While there has been much recent work studying how linguistic information is encoded in pre-trained sentence representations, comparatively little is understood about how these models change when adapted to solve downstream tasks. Using a…

Computation and Language · Computer Science 2020-05-01 Amil Merchant , Elahe Rahimtoroghi , Ellie Pavlick , Ian Tenney

Unsupervised pretraining models have been shown to facilitate a wide range of downstream NLP applications. These models, however, retain some of the limitations of traditional static word embeddings. In particular, they encode only the…

Computation and Language · Computer Science 2020-04-21 Anne Lauscher , Ivan Vulić , Edoardo Maria Ponti , Anna Korhonen , Goran Glavaš

As a pre-trained Transformer model, BERT (Bidirectional Encoder Representations from Transformers) has achieved ground-breaking performance on multiple NLP tasks. On the other hand, Boosting is a popular ensemble learning technique which…

Computation and Language · Computer Science 2020-09-15 Tongwen Huang , Qingyun She , Junlin Zhang

Recently, the development of pre-trained language models has brought natural language processing (NLP) tasks to the new state-of-the-art. In this paper we explore the efficiency of various pre-trained language models. We pre-train a list of…

Computation and Language · Computer Science 2023-07-27 Tong Guo

Resource-constrained devices are increasingly the deployment targets of machine learning applications. Static models, however, do not always suffice for dynamic environments. On-device training of models allows for quick adaptability to new…

Machine Learning · Computer Science 2023-01-10 Danilo Vucetic , Mohammadreza Tayaranian , Maryam Ziaeefard , James J. Clark , Brett H. Meyer , Warren J. Gross

A growing trend has emerged in designing high-quality Small Language Models (SLMs) with a few million parameters. This trend is driven by the increasing concerns over cloud costs, privacy, and latency. Considering that full parameter…

Machine Learning · Computer Science 2025-07-03 Xuan Shen , Peiyan Dong , Zhenglun Kong , Yifan Gong , Changdi Yang , Zhaoyang Han , Yanyue Xie , Lei Lu , Cheng Lyu , Chao Wu , Yanzhi Wang , Pu Zhao

Pre-trained language models such as BERT have exhibited remarkable performances in many tasks in natural language understanding (NLU). The tokens in the models are usually fine-grained in the sense that for languages like English they are…

Computation and Language · Computer Science 2021-05-28 Xinsong Zhang , Pengshuai Li , Hang Li

Fine-tuning pre-trained language models (PTLMs), such as BERT and its better variant RoBERTa, has been a common practice for advancing performance in natural language understanding (NLU) tasks. Recent advance in representation learning…

Computation and Language · Computer Science 2021-02-05 Wenxuan Zhou , Bill Yuchen Lin , Xiang Ren

More recently, Bidirectional Encoder Representations from Transformers (BERT) was proposed and has achieved impressive success on many natural language processing (NLP) tasks such as question answering and language understanding, due mainly…

Computation and Language · Computer Science 2021-04-13 Shih-Hsuan Chiu , Berlin Chen

Pretrained neural models such as BERT, when fine-tuned to perform natural language inference (NLI), often show high accuracy on standard datasets, but display a surprising lack of sensitivity to word order on controlled challenge sets. We…

Computation and Language · Computer Science 2020-04-28 Junghyun Min , R. Thomas McCoy , Dipanjan Das , Emily Pitler , Tal Linzen

Recently, Natural Language Processing (NLP) has witnessed an impressive progress in many areas, due to the advent of novel, pretrained contextual representation models. In particular, Devlin et al. (2019) proposed a model, called BERT…

Computation and Language · Computer Science 2020-03-09 Debora Nozza , Federico Bianchi , Dirk Hovy

Introducing BERT into cross-modal settings raises difficulties in its optimization for handling multiple modalities. Both the BERT architecture and training objective need to be adapted to incorporate and model information from different…

Computer Vision and Pattern Recognition · Computer Science 2023-12-11 Xin Li , Peng Li , Zeyong Wei , Zhe Zhu , Mingqiang Wei , Junhui Hou , Liangliang Nan , Jing Qin , Haoran Xie , Fu Lee Wang

Probing complex language models has recently revealed several insights into linguistic and semantic patterns found in the learned representations. In this article, we probe BERT specifically to understand and measure the relational…

Computation and Language · Computer Science 2021-09-09 Jonas Wallat , Jaspreet Singh , Avishek Anand

As large language models (LLMs) continue to scale, deployment is increasingly bottlenecked by the memory wall, motivating a shift toward extremely low-bit quantization. However, most quantization-aware training (QAT) methods apply hard…

Machine Learning · Computer Science 2026-01-29 Guoan Wang , Feiyu Wang , Zongwei Lv , Yikun Zong , Tong Yang

Adapting pre-trained neural models to downstream tasks has become the standard practice for obtaining high-quality models. In this work, we propose a novel model adaptation paradigm, adapting by pruning, which prunes neural connections in…

Machine Learning · Computer Science 2021-05-10 Yang Gao , Nicolo Colombo , Wei Wang

BERT-based models have shown a remarkable ability in the Chinese Spelling Check (CSC) task recently. However, traditional BERT-based methods still suffer from two limitations. First, although previous works have identified that explicit…

Computation and Language · Computer Science 2023-12-29 Yongchang Cao , Liang He , Zhen Wu , Xinyu Dai

The Bidirectional Encoder Representations from Transformers (BERT) model has achieved the state-of-the-art performance for many natural language processing (NLP) tasks. Yet, limited research has been contributed to studying its…

Computation and Language · Computer Science 2021-09-23 Zimin Wan , Chenchen Xu , Hanna Suominen

Natural Language Processing (NLP) has witnessed a transformative leap with the advent of transformer-based architectures, which have significantly enhanced the ability of machines to understand and generate human-like text. This paper…

Computation and Language · Computer Science 2025-03-27 Tianhao Wu , Yu Wang , Ngoc Quach

The success of bidirectional encoders using masked language models, such as BERT, on numerous natural language processing tasks has prompted researchers to attempt to incorporate these pre-trained models into neural machine translation…

Computation and Language · Computer Science 2021-09-13 Haoran Xu , Benjamin Van Durme , Kenton Murray