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