English
Related papers

Related papers: CEEBERT: Cross-Domain Inference in Early Exit BERT

200 papers

Pre-trained language models (PLMs) aim to learn universal language representations by conducting self-supervised training tasks on large-scale corpora. Since PLMs capture word semantics in different contexts, the quality of word…

Computation and Language · Computer Science 2022-03-22 Wenhao Yu , Chenguang Zhu , Yuwei Fang , Donghan Yu , Shuohang Wang , Yichong Xu , Michael Zeng , Meng Jiang

Recently, knowledge-enhanced pre-trained language models (KEPLMs) improve context-aware representations via learning from structured relations in knowledge graphs, and/or linguistic knowledge from syntactic or dependency analysis. Unlike…

Computation and Language · Computer Science 2022-10-13 Taolin Zhang , Junwei Dong , Jianing Wang , Chengyu Wang , Ang Wang , Yinghui Liu , Jun Huang , Yong Li , Xiaofeng He

We present SpanBERT, a pre-training method that is designed to better represent and predict spans of text. Our approach extends BERT by (1) masking contiguous random spans, rather than random tokens, and (2) training the span boundary…

Computation and Language · Computer Science 2020-01-22 Mandar Joshi , Danqi Chen , Yinhan Liu , Daniel S. Weld , Luke Zettlemoyer , Omer Levy

Deep neural networks have long training and processing times. Early exits added to neural networks allow the network to make early predictions using intermediate activations in the network in time-sensitive applications. However, early…

Machine Learning · Computer Science 2022-12-27 Devdhar Patel , Hava Siegelmann

This paper presents ExeGPT, a distributed system designed for constraint-aware LLM inference. ExeGPT finds and runs with an optimal execution schedule to maximize inference throughput while satisfying a given latency constraint. By…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-04-12 Hyungjun Oh , Kihong Kim , Jaemin Kim , Sungkyun Kim , Junyeol Lee , Du-seong Chang , Jiwon Seo

Large language models can produce powerful contextual representations that lead to improvements across many NLP tasks. Since these models are typically guided by a sequence of learned self attention mechanisms and may comprise undesired…

Computation and Language · Computer Science 2019-10-14 Benjamin Hoover , Hendrik Strobelt , Sebastian Gehrmann

Pre-trained transformer models are the current state-of-the-art for natural language models processing. seBERT is such a model, that was developed based on the BERT architecture, but trained from scratch with software engineering data. We…

Software Engineering · Computer Science 2022-05-04 Alexander Trautsch , Steffen Herbold

Language model pre-training, such as BERT, has achieved remarkable results in many NLP tasks. However, it is unclear why the pre-training-then-fine-tuning paradigm can improve performance and generalization capability across different…

Computation and Language · Computer Science 2019-08-16 Yaru Hao , Li Dong , Furu Wei , Ke Xu

Lexicon information and pre-trained models, such as BERT, have been combined to explore Chinese sequence labelling tasks due to their respective strengths. However, existing methods solely fuse lexicon features via a shallow and random…

Computation and Language · Computer Science 2021-12-28 Wei Liu , Xiyan Fu , Yue Zhang , Wenming Xiao

To tackle the high inference latency exhibited by autoregressive language models, previous studies have proposed an early-exiting framework that allocates adaptive computation paths for each token based on the complexity of generating the…

Computation and Language · Computer Science 2023-10-10 Sangmin Bae , Jongwoo Ko , Hwanjun Song , Se-Young Yun

This study compares the effectiveness and robustness of multi-class categorization of Amazon product data using transfer learning on pre-trained contextualized language models. Specifically, we fine-tuned BERT and XLNet, two bidirectional…

Machine Learning · Statistics 2019-09-24 Xinyi Liu , Artit Wangperawong

Transformer-based self-supervised models are trained as feature extractors and have empowered many downstream speech tasks to achieve state-of-the-art performance. However, both the training and inference process of these models may…

Computation and Language · Computer Science 2021-05-04 Jinchuan Tian , Rongzhi Gu , Helin Wang , Yuexian Zou

We present BlockBERT, a lightweight and efficient BERT model for better modeling long-distance dependencies. Our model extends BERT by introducing sparse block structures into the attention matrix to reduce both memory consumption and…

Computation and Language · Computer Science 2020-11-03 Jiezhong Qiu , Hao Ma , Omer Levy , Scott Wen-tau Yih , Sinong Wang , Jie Tang

Pre-trained language models (PLMs) like BERT have made great progress in NLP. News articles usually contain rich textual information, and PLMs have the potentials to enhance news text modeling for various intelligent news applications like…

Computation and Language · Computer Science 2021-09-03 Chuhan Wu , Fangzhao Wu , Yang Yu , Tao Qi , Yongfeng Huang , Qi Liu

Pre-trained Language Models (PLMs) have achieved remarkable performance on diverse NLP tasks through pre-training and fine-tuning. However, fine-tuning the model with a large number of parameters on limited downstream datasets often leads…

Computation and Language · Computer Science 2025-05-13 Mihyeon Kim , Juhyoung Park , Youngbin Kim

Prompt learning represents a promising method for adapting pre-trained vision-language models (VLMs) to various downstream tasks by learning a set of text embeddings. One challenge inherent to these methods is the poor generalization…

Computer Vision and Pattern Recognition · Computer Science 2024-11-18 Fangming Cui , Xun Yang , Chao Wu , Liang Xiao , Xinmei Tian

In recent years, Vision-Language Models (VLMs) have shown remarkable performance improvements in Vision-Language tasks. However, their large size poses challenges for real-world applications where inference latency is a concern. To tackle…

Machine Learning · Computer Science 2025-06-10 Divya Jyoti Bajpai , Manjesh Kumar Hanawal

As Large Language Models (LLMs) achieve remarkable empirical success through scaling model and data size, pretraining has become increasingly critical yet computationally prohibitive, hindering rapid development. Despite the availability of…

Computation and Language · Computer Science 2026-02-06 Ji Zhao , Yufei Gu , Shitong Shao , Xun Zhou , Liang Xiang , Zeke Xie

This paper investigates the effectiveness of pre-training for few-shot intent classification. While existing paradigms commonly further pre-train language models such as BERT on a vast amount of unlabeled corpus, we find it highly effective…

Computation and Language · Computer Science 2024-09-17 Haode Zhang , Yuwei Zhang , Li-Ming Zhan , Jiaxin Chen , Guangyuan Shi , Albert Y. S. Lam , Xiao-Ming Wu

Increasing the size of large language models (LLMs) has been shown to lead to better performance. However, this comes at the cost of slower and more expensive inference. Early-exiting is a promising approach for improving the efficiency of…

Computation and Language · Computer Science 2024-10-31 Jort Vincenti , Karim Abdel Sadek , Joan Velja , Matteo Nulli , Metod Jazbec