Related papers: LRC-BERT: Latent-representation Contrastive Knowle…

Cross-language pre-trained models such as multilingual BERT (mBERT) have achieved significant performance in various cross-lingual downstream NLP tasks. This paper proposes a multi-level contrastive learning (ML-CTL) framework to further…

Pretrained language models have led to significant performance gains in many NLP tasks. However, the intensive computing resources to train such models remain an issue. Knowledge distillation alleviates this problem by learning a…

Pre-trained language models (PLMs) achieve great success in NLP. However, their huge model sizes hinder their applications in many practical systems. Knowledge distillation is a popular technique to compress PLMs, which learns a small…

This paper studies compressing pre-trained language models, like BERT (Devlin et al.,2019), via teacher-student knowledge distillation. Previous works usually force the student model to strictly mimic the smoothed labels predicted by the…

In this paper, we propose a simple yet effective contrastive knowledge distillation framework that achieves sample-wise logit alignment while preserving semantic consistency. Conventional knowledge distillation approaches exhibit…

Knowledge distillation from large language models (LLMs) assumes that the teacher's output distribution is a high-quality training signal. On reasoning tasks, this assumption is frequently violated. A model's intermediate representations…

Large language models (LLMs) excel at clinical information extraction but their computational demands limit practical deployment. Knowledge distillation--the process of transferring knowledge from larger to smaller models--offers a…

This paper presents UniBERT, a compact multilingual language model that uses an innovative training framework that integrates three components: masked language modeling, adversarial training, and knowledge distillation. Pre-trained on a…

Self-supervised speech representation learning methods like wav2vec 2.0 and Hidden-unit BERT (HuBERT) leverage unlabeled speech data for pre-training and offer good representations for numerous speech processing tasks. Despite the success…

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…

Connectionist temporal classification (CTC) -based models are attractive because of their fast inference in automatic speech recognition (ASR). Language model (LM) integration approaches such as shallow fusion and rescoring can improve the…

This paper proposes the DistillCSE framework, which performs contrastive learning under the self-training paradigm with knowledge distillation. The potential advantage of DistillCSE is its self-enhancing feature: using a base model to…

This study aims at solving the Machine Reading Comprehension problem where questions have to be answered given a context passage. The challenge is to develop a computationally faster model which will have improved inference time. State of…

Although large-scale pretrained language models, such as BERT and RoBERTa, have achieved superhuman performance on in-distribution test sets, their performance suffers on out-of-distribution test sets (e.g., on contrast sets). Building…

Neural Machine Translation (NMT) models achieve state-of-the-art performance on many translation benchmarks. As an active research field in NMT, knowledge distillation is widely applied to enhance the model's performance by transferring…

In this paper, we propose Stochastic Knowledge Distillation (SKD) to obtain compact BERT-style language model dubbed SKDBERT. In each iteration, SKD samples a teacher model from a pre-defined teacher ensemble, which consists of multiple…

Recent advances in pre-training huge models on large amounts of text through self supervision have obtained state-of-the-art results in various natural language processing tasks. However, these huge and expensive models are difficult to use…

Benefiting from the sequence-level knowledge distillation, the Non-Autoregressive Transformer (NAT) achieves great success in neural machine translation tasks. However, existing knowledge distillation has side effects, such as propagating…

The performance of autoregressive models on natural language generation tasks has dramatically improved due to the adoption of deep, self-attentive architectures. However, these gains have come at the cost of hindering inference speed,…

Knowledge distillation (KD) is a highly promising method for mitigating the computational problems of pre-trained language models (PLMs). Among various KD approaches, Intermediate Layer Distillation (ILD) has been a de facto standard KD…