English
Related papers

Related papers: TernaryBERT: Distillation-aware Ultra-low Bit BERT

200 papers

Fine-tuned transformer models have shown superior performances in many natural language tasks. However, the large model size prohibits deploying high-performance transformer models on resource-constrained devices. This paper proposes a…

Computation and Language · Computer Science 2024-10-01 Zi Yang , Samridhi Choudhary , Siegfried Kunzmann , Zheng Zhang

Methods for improving the efficiency of deep network training (i.e. the resources required to achieve a given level of model quality) are of immediate benefit to deep learning practitioners. Distillation is typically used to compress models…

Machine Learning · Computer Science 2022-11-03 Cody Blakeney , Jessica Zosa Forde , Jonathan Frankle , Ziliang Zong , Matthew L. Leavitt

In light of the success of transferring language models into NLP tasks, we ask whether the full BERT model is always the best and does it exist a simple but effective method to find the winning ticket in state-of-the-art deep neural…

Computation and Language · Computer Science 2022-01-21 Jing Fan , Xin Zhang , Sheng Zhang , Yan Pan , Lixiang Guo

Biomedical literature is a rapidly expanding field of science and technology. Classification of biomedical texts is an essential part of biomedicine research, especially in the field of biology. This work proposes the fine-tuned DistilBERT,…

Computation and Language · Computer Science 2024-04-23 Ziqing Guo

Knowledge distillation has been proven to be effective in model acceleration and compression. It allows a small network to learn to generalize in the same way as a large network. Recent successes in pre-training suggest the effectiveness of…

Computation and Language · Computer Science 2021-07-20 Ye Lin , Yanyang Li , Ziyang Wang , Bei Li , Quan Du , Tong Xiao , Jingbo Zhu

For self-supervised speech processing, it is crucial to use pretrained models as speech representation extractors. In recent works, increasing the size of the model has been utilized in acoustic model training in order to achieve better…

Audio and Speech Processing · Electrical Eng. & Systems 2021-05-04 Po-Han Chi , Pei-Hung Chung , Tsung-Han Wu , Chun-Cheng Hsieh , Yen-Hao Chen , Shang-Wen Li , Hung-yi Lee

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

Pre-trained Transformer models such as BERT have shown great success in a wide range of applications, but at the cost of substantial increases in model complexity. Quantization-aware training (QAT) is a promising method to lower the…

Computation and Language · Computer Science 2023-02-24 Minsoo Kim , Kyuhong Shim , Seongmin Park , Wonyong Sung , Jungwook Choi

Bidirectional Encoder Representations from Transformers (BERT) represents the latest incarnation of pretrained language models which have recently advanced a wide range of natural language processing tasks. In this paper, we showcase how…

Computation and Language · Computer Science 2019-09-06 Yang Liu , Mirella Lapata

The huge size of deep networks hinders their use in small computing devices. In this paper, we consider compressing the network by weight quantization. We extend a recently proposed loss-aware weight binarization scheme to ternarization,…

Machine Learning · Computer Science 2018-05-11 Lu Hou , James T. Kwok

Pre-trained language models (e.g., BERT) have achieved significant success in various natural language processing (NLP) tasks. However, high storage and computational costs obstruct pre-trained language models to be effectively deployed on…

Computation and Language · Computer Science 2020-10-14 Jianquan Li , Xiaokang Liu , Honghong Zhao , Ruifeng Xu , Min Yang , Yaohong Jin

In this paper, we introduce TextBrewer, an open-source knowledge distillation toolkit designed for natural language processing. It works with different neural network models and supports various kinds of supervised learning tasks, such as…

Computation and Language · Computer Science 2020-12-14 Ziqing Yang , Yiming Cui , Zhipeng Chen , Wanxiang Che , Ting Liu , Shijin Wang , Guoping Hu

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

The front-end module in a typical Mandarin text-to-speech system (TTS) is composed of a long pipeline of text processing components, which requires extensive efforts to build and is prone to large accumulative model size and cascade errors.…

Sound · Computer Science 2021-01-01 Yang Zhang , Liqun Deng , Yasheng Wang

As pretrained transformer language models continue to achieve state-of-the-art performance, the Natural Language Processing community has pushed for advances in model compression and efficient attention mechanisms to address high…

Computation and Language · Computer Science 2023-11-27 Nathan Brown , Ashton Williamson , Tahj Anderson , Logan Lawrence

We propose a process to compress a pre-trained Vision Language Model into a ternary version of itself instead of training a ternary model from scratch. A new initialization scheme from pre-trained weights based on the k-means algorithm is…

Computer Vision and Pattern Recognition · Computer Science 2025-04-10 Ben Crulis , Cyril De Runz , Barthelemy Serres , Gilles Venturini

Transformer-based pre-trained language models such as BERT have achieved remarkable results in Semantic Sentence Matching. However, existing models still suffer from insufficient ability to capture subtle differences. Minor noise like word…

Computation and Language · Computer Science 2023-04-17 Sirui Wang , Di Liang , Jian Song , Yuntao Li , Wei Wu

Specialised pre-trained language models are becoming more frequent in NLP since they can potentially outperform models trained on generic texts. BioBERT and BioClinicalBERT are two examples of such models that have shown promise in medical…

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

Second-pass rescoring is employed in most state-of-the-art speech recognition systems. Recently, BERT based models have gained popularity for re-ranking the n-best hypothesis by exploiting the knowledge from masked language model…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-19 Prashanth Gurunath Shivakumar , Jari Kolehmainen , Yile Gu , Ankur Gandhe , Ariya Rastrow , Ivan Bulyko
‹ Prev 1 4 5 6 7 8 10 Next ›