English
Related papers

Related papers: Understanding and Improving Lexical Choice in Non-…

200 papers

Sequence-level knowledge distillation (SLKD) is a model compression technique that leverages large, accurate teacher models to train smaller, under-parameterized student models. Why does pre-processing MT data with SLKD help us train…

Computation and Language · Computer Science 2019-12-10 Mitchell A. Gordon , Kevin Duh

We present Knowledge Distillation with Meta Learning (MetaDistil), a simple yet effective alternative to traditional knowledge distillation (KD) methods where the teacher model is fixed during training. We show the teacher network can learn…

Machine Learning · Computer Science 2022-04-05 Wangchunshu Zhou , Canwen Xu , Julian McAuley

Knowledge Distillation (KD) is a model-agnostic technique to improve model quality while having a fixed capacity budget. It is a commonly used technique for model compression, where a larger capacity teacher model with better quality is…

Machine Learning · Computer Science 2021-03-02 Jiaxi Tang , Rakesh Shivanna , Zhe Zhao , Dong Lin , Anima Singh , Ed H. Chi , Sagar Jain

Recent studies have focused on leveraging large-scale artificial intelligence (LAI) models to improve semantic representation and compression capabilities. However, the substantial computational demands of LAI models pose significant…

Machine Learning · Computer Science 2025-06-17 Chuanhong Liu , Caili Guo , Yang Yang , Mingzhe Chen , Tony Q. S. Quek

Pre-trained language models such as BERT have proven to be highly effective for natural language processing (NLP) tasks. However, the high demand for computing resources in training such models hinders their application in practice. In…

Computation and Language · Computer Science 2019-08-27 Siqi Sun , Yu Cheng , Zhe Gan , Jingjing Liu

In recent years, there has been a great deal of research in developing end-to-end speech recognition models, which enable simplifying the traditional pipeline and achieving promising results. Despite their remarkable performance…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-20 Ji Won Yoon , Hyeonseung Lee , Hyung Yong Kim , Won Ik Cho , Nam Soo Kim

Knowledge distillation (KD) is a very popular method for model size reduction. Recently, the technique is exploited for quantized deep neural networks (QDNNs) training as a way to restore the performance sacrificed by word-length reduction.…

Machine Learning · Computer Science 2019-10-24 Sungho Shin , Yoonho Boo , Wonyong Sung

Knowledge Distillation (KD) is a prominent neural model compression technique that heavily relies on teacher network predictions to guide the training of a student model. Considering the ever-growing size of pre-trained language models…

Machine Learning · Computer Science 2023-04-13 Ivan Kobyzev , Aref Jafari , Mehdi Rezagholizadeh , Tianda Li , Alan Do-Omri , Peng Lu , Pascal Poupart , Ali Ghodsi

Knowledge distillation (KD), transferring knowledge from a cumbersome teacher model to a lightweight student model, has been investigated to design efficient neural architectures. Generally, the objective function of KD is the…

Machine Learning · Computer Science 2021-05-20 Taehyeon Kim , Jaehoon Oh , NakYil Kim , Sangwook Cho , Se-Young Yun

Non-autoregressive Transformers (NATs) reduce the inference latency of Autoregressive Transformers (ATs) by predicting words all at once rather than in sequential order. They have achieved remarkable progress in machine translation as well…

Computation and Language · Computer Science 2023-06-05 Chenxin An , Jiangtao Feng , Fei Huang , Xipeng Qiu , Lingpeng Kong

Non-autoregressive (NAR) language models are known for their low latency in neural machine translation (NMT). However, a performance gap exists between NAR and autoregressive models due to the large decoding space and difficulty in…

Computation and Language · Computer Science 2024-07-03 Hao Wang , Tetsuro Morimura , Ukyo Honda , Daisuke Kawahara

This paper studies the problem of pre-training for small models, which is essential for many mobile devices. Current state-of-the-art methods on this problem transfer the representational knowledge of a large network (as a Teacher) into a…

Computer Vision and Pattern Recognition · Computer Science 2024-06-18 Mingsheng Li , Lin Zhang , Mingzhen Zhu , Zilong Huang , Gang Yu , Jiayuan Fan , Tao Chen

End-to-end automatic speech translation (AST) relies on data that combines audio inputs with text translation outputs. Previous work used existing large parallel corpora of transcriptions and translations in a knowledge distillation (KD)…

Computation and Language · Computer Science 2023-07-18 Rebekka Hubert , Artem Sokolov , Stefan Riezler

Knowledge Distillation (KD) is a powerful technique for transferring knowledge between neural network models, where a pre-trained teacher model is used to facilitate the training of the target student model. However, the availability of a…

Computer Vision and Pattern Recognition · Computer Science 2023-05-17 Xucong Wang , Pengchao Han , Lei Guo

Knowledge distillation (KD) is an effective method for model compression and transferring knowledge between models. However, its effect on model's robustness against spurious correlations that degrade performance on out-of-distribution data…

Machine Learning · Computer Science 2025-10-31 Jiali Cheng , Chirag Agarwal , Hadi Amiri

Large-scale language models have recently demonstrated impressive empirical performance. Nevertheless, the improved results are attained at the price of bigger models, more power consumption, and slower inference, which hinder their…

Computation and Language · Computer Science 2021-03-18 Kevin J Liang , Weituo Hao , Dinghan Shen , Yufan Zhou , Weizhu Chen , Changyou Chen , Lawrence Carin

Knowledge Distillation (KD) transfers knowledge from a large pre-trained teacher network to a compact and efficient student network, making it suitable for deployment on resource-limited media terminals. However, traditional KD methods…

Computer Vision and Pattern Recognition · Computer Science 2024-09-23 Xinlei Huang , Jialiang Tang , Xubin Zheng , Jinjia Zhou , Wenxin Yu , Ning Jiang

Non-autoregressive approaches aim to improve the inference speed of translation models, particularly those that generate output in a one-pass forward manner. However, these approaches often suffer from a significant drop in translation…

Computation and Language · Computer Science 2024-10-15 Shen-sian Syu , Juncheng Xie , Hung-yi Lee

Knowledge Distillation (KD) has been extensively used for natural language understanding (NLU) tasks to improve a small model's (a student) generalization by transferring the knowledge from a larger model (a teacher). Although KD methods…

Machine Learning · Computer Science 2022-12-13 Aref Jafari , Ivan Kobyzev , Mehdi Rezagholizadeh , Pascal Poupart , Ali Ghodsi

Knowledge distillation (KD) is used to enhance automatic speaker verification performance by ensuring consistency between large teacher networks and lightweight student networks at the embedding level or label level. However, the…

Sound · Computer Science 2024-06-28 Duc-Tuan Truong , Ruijie Tao , Jia Qi Yip , Kong Aik Lee , Eng Siong Chng