English
Related papers

Related papers: LadaBERT: Lightweight Adaptation of BERT through H…

200 papers

Pre-trained language models like BERT have achieved great success in a wide variety of NLP tasks, while the superior performance comes with high demand in computational resources, which hinders the application in low-latency IR systems. We…

Information Retrieval · Computer Science 2020-02-18 Wenhao Lu , Jian Jiao , Ruofei Zhang

In this paper, we introduce a new vision-language pre-trained model -- ImageBERT -- for image-text joint embedding. Our model is a Transformer-based model, which takes different modalities as input and models the relationship between them.…

Computer Vision and Pattern Recognition · Computer Science 2020-01-24 Di Qi , Lin Su , Jia Song , Edward Cui , Taroon Bharti , Arun Sacheti

Knowledge distillation is an approach to transfer information on representations from a teacher to a student by reducing their difference. A challenge of this approach is to reduce the flexibility of the student's representations inducing…

Computation and Language · Computer Science 2024-10-28 Hee-Jun Jung , Doyeon Kim , Seung-Hoon Na , Kangil Kim

Representations derived from models such as BERT (Bidirectional Encoder Representations from Transformers) and HuBERT (Hidden units BERT), have helped to achieve state-of-the-art performance in dimensional speech emotion recognition.…

Sound · Computer Science 2023-12-29 Vikramjit Mitra , Jingping Nie , Erdrin Azemi

Language models are pre-trained using large corpora of generic data like book corpus, common crawl and Wikipedia, which is essential for the model to understand the linguistic characteristics of the language. New studies suggest using…

Computation and Language · Computer Science 2022-09-28 Arnav Ladkat , Aamir Miyajiwala , Samiksha Jagadale , Rekha Kulkarni , Raviraj Joshi

Language models have proven successful across a wide range of software engineering tasks, but their significant computational costs often hinder their practical adoption. To address this challenge, researchers have begun applying various…

Software Engineering · Computer Science 2024-12-19 Giordano d'Aloisio , Luca Traini , Federica Sarro , Antinisca Di Marco

Heavily pre-trained transformer models such as BERT have recently shown to be remarkably powerful at language modelling by achieving impressive results on numerous downstream tasks. It has also been shown that they are able to implicitly…

Information Retrieval · Computer Science 2021-03-05 Gustavo Penha , Claudia Hauff

Recently, knowledge distillation (KD) has shown great success in BERT compression. Instead of only learning from the teacher's soft label as in conventional KD, researchers find that the rich information contained in the hidden layers of…

Computation and Language · Computer Science 2021-06-11 Yuanxin Liu , Fandong Meng , Zheng Lin , Weiping Wang , Jie Zhou

This paper presents a novel knowledge distillation based model compression framework consisting of a student ensemble. It enables distillation of simultaneously learnt ensemble knowledge onto each of the compressed student models. Each…

Computer Vision and Pattern Recognition · Computer Science 2020-11-17 Devesh Walawalkar , Zhiqiang Shen , Marios Savvides

In this paper, we propose Stacked DeBERT, short for Stacked Denoising Bidirectional Encoder Representations from Transformers. This novel model improves robustness in incomplete data, when compared to existing systems, by designing a novel…

Computation and Language · Computer Science 2021-01-15 Gwenaelle Cunha Sergio , Minho Lee

In Natural Language Processing (NLP), Transformers have already revolutionized the field by utilizing an attention-based encoder-decoder model. Recently, some pioneering works have employed Transformer-like architectures in Computer Vision…

Computer Vision and Pattern Recognition · Computer Science 2024-02-13 Gousia Habib , Tausifa Jan Saleem , Brejesh Lall

We present, to our knowledge, the first application of BERT to document classification. A few characteristics of the task might lead one to think that BERT is not the most appropriate model: syntactic structures matter less for content…

Computation and Language · Computer Science 2019-08-23 Ashutosh Adhikari , Achyudh Ram , Raphael Tang , Jimmy Lin

We introduce HUBERT which combines the structured-representational power of Tensor-Product Representations (TPRs) and BERT, a pre-trained bidirectional Transformer language model. We show that there is shared structure between different NLP…

Computation and Language · Computer Science 2021-04-27 Mehrad Moradshahi , Hamid Palangi , Monica S. Lam , Paul Smolensky , Jianfeng Gao

Large pretrained language models such as BERT suffer from slow inference and high memory usage, due to their huge size. Recent approaches to compressing BERT rely on iterative pruning and knowledge distillation, which, however, are often…

Computation and Language · Computer Science 2025-02-07 Hyemin Lim , Jaeyeon Lee , Dong-Wan Choi

Pre-trained language representation models, such as BERT, capture a general language representation from large-scale corpora, but lack domain-specific knowledge. When reading a domain text, experts make inferences with relevant knowledge.…

Computation and Language · Computer Science 2019-09-18 Weijie Liu , Peng Zhou , Zhe Zhao , Zhiruo Wang , Qi Ju , Haotang Deng , Ping Wang

This work explores optimizing transformer-based language models by integrating model compression techniques with inhibitor attention, a novel alternative attention mechanism. Inhibitor attention employs Manhattan distances and ReLU…

Computation and Language · Computer Science 2025-03-21 Tony Zhang , Rickard Brännvall

Modern search systems use several large ranker models with transformer architectures. These models require large computational resources and are not suitable for usage on devices with limited computational resources. Knowledge distillation…

Attention-based sequence-to-sequence (seq2seq) models have achieved promising results in automatic speech recognition (ASR). However, as these models decode in a left-to-right way, they do not have access to context on the right. We…

Computation and Language · Computer Science 2020-08-11 Hayato Futami , Hirofumi Inaguma , Sei Ueno , Masato Mimura , Shinsuke Sakai , Tatsuya Kawahara

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

Large-scale speech self-supervised learning (SSL) has emerged to the main field of speech processing, however, the problem of computational cost arising from its vast size makes a high entry barrier to academia. In addition, existing…

Audio and Speech Processing · Electrical Eng. & Systems 2022-07-04 Yeonghyeon Lee , Kangwook Jang , Jahyun Goo , Youngmoon Jung , Hoirin Kim