Related papers: BERT2DNN: BERT Distillation with Massive Unlabeled…
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…
We address the challenge of getting efficient yet accurate recognition systems with limited labels. While recognition models improve with model size and amount of data, many specialized applications of computer vision have severe resource…
This study proposes a knowledge distillation algorithm based on large language models and feature alignment, aiming to effectively transfer the knowledge of large pre-trained models into lightweight student models, thereby reducing…
BERT-based text ranking models have dramatically advanced the state-of-the-art in ad-hoc retrieval, wherein most models tend to consider individual query-document pairs independently. In the mean time, the importance and usefulness to…
Knowledge distillation is typically realized by transferring a teacher model's knowledge into a student's parameters through supervised or reinforcement-based optimization. While effective, such approaches require repeated parameter updates…
Sentiment classification in short text datasets faces significant challenges such as class imbalance, limited training samples, and the inherent subjectivity of sentiment labels -- issues that are further intensified by the limited context…
A pre-trained language model, BERT, has brought significant performance improvements across a range of natural language processing tasks. Since the model is trained on a large corpus of diverse topics, it shows robust performance for domain…
Deep pre-training and fine-tuning models (like BERT, OpenAI GPT) have demonstrated excellent results in question answering areas. However, due to the sheer amount of model parameters, the inference speed of these models is very slow. How to…
Large transformer models, such as BERT, achieve state-of-the-art results in machine reading comprehension (MRC) for open-domain question answering (QA). However, transformers have a high computational cost for inference which makes them…
The major task of any e-commerce search engine is to retrieve the most relevant inventory items, which best match the user intent reflected in a query. This task is non-trivial due to many reasons, including ambiguous queries, misaligned…
Recently, pre-trained contextual models, such as BERT, have shown to perform well in language related tasks. We revisit the design decisions that govern the applicability of these models for the passage re-ranking task in open-domain…
Knowledge distillation usually transfers the knowledge from a pre-trained cumbersome teacher network to a compact student network, which follows the classical teacher-teaching-student paradigm. Based on this paradigm, previous methods…
Much of the focus in the area of knowledge distillation has been on distilling knowledge from a larger teacher network to a smaller student network. However, there has been little research on how the concept of distillation can be leveraged…
Data-centric distillation, including data augmentation, selection, and mixing, offers a promising path to creating smaller, more efficient student Large Language Models (LLMs) that retain strong reasoning abilities. However, there still…
This study presents a novel approach for knowledge distillation (KD) from a BERT teacher model to an automatic speech recognition (ASR) model using intermediate layers. To distil the teacher's knowledge, we use an attention decoder that…
Transformer based Very Large Language Models (VLLMs) like BERT, XLNet and RoBERTa, have recently shown tremendous performance on a large variety of Natural Language Understanding (NLU) tasks. However, due to their size, these VLLMs are…
Dataset distillation aims at synthesizing a dataset by a small number of artificially generated data items, which, when used as training data, reproduce or approximate a machine learning (ML) model as if it were trained on the entire…
Recent developments in natural language representations have been accompanied by large and expensive models that leverage vast amounts of general-domain text through self-supervised pre-training. Due to the cost of applying such models to…
Self-supervised pre-trained models such as HuBERT and WavLM leverage unlabeled speech data for representation learning and offer significantly improve for numerous downstream tasks. Despite the success of these methods, their large memory…
Optimizing neural networks with noisy labels is a challenging task, especially if the label set contains real-world noise. Networks tend to generalize to reasonable patterns in the early training stages and overfit to specific details of…