相关论文: Distilling BERT for low complexity network trainin…

Topic segmentation is critical in key NLP tasks and recent works favor highly effective neural supervised approaches. However, current neural solutions are arguably limited in how they model context. In this paper, we enhance a segmenter…

Long short-term memory (LSTM) is a robust recurrent neural network architecture for learning spatiotemporal sequential data. However, it requires significant computational power for learning and implementing from both software and hardware…

One of the most computationally intensive parts in modern recognition systems is an inference of deep neural networks that are used for image classification, segmentation, enhancement, and recognition. The growing popularity of edge…

The rise of big data analytics on top of NLP increases the computational burden for text processing at scale. The problems faced in NLP are very high dimensional text, so it takes a high computation resource. The MapReduce allows…

Detecting plagiarism involves finding similar items in two different sources. In this article, we propose a novel method for detecting plagiarism that is based on attention mechanism-based long short-term memory (LSTM) and bidirectional…

This paper uses the BERT model, which is a transformer-based architecture, to solve task 4A, English Language, Sentiment Analysis in Twitter of SemEval2017. BERT is a very powerful large language model for classification tasks when the…

The Bidirectional Encoder Representations from Transformers (BERT) model has achieved the state-of-the-art performance for many natural language processing (NLP) tasks. Yet, limited research has been contributed to studying its…

Methods for improving the efficiency of deep network training (i.e. the resources required to achieve a given level of model quality) are of immediate benefit to deep learning practitioners. Distillation is typically used to compress models…

We study clinical Named Entity Recognition (NER) on the CADEC corpus and compare three families of approaches: (i) BERT-style encoders (BERT Base, BioClinicalBERT, RoBERTa-large), (ii) GPT-4o used with few-shot in-context learning (ICL)…

Accurate classification of multipartite entanglement in high-dimensional quantum systems is crucial for advancing quantum communication and information processing. However, conventional methods are resource-intensive, and even many…

Scientist learn early on how to cite scientific sources to support their claims. Sometimes, however, scientists have challenges determining where a citation should be situated -- or, even worse, fail to cite a source altogether.…

This paper describes an analytical modeling tool called Bitlet that can be used, in a parameterized fashion, to understand the affinity of workloads to processing-in-memory (PIM) as opposed to traditional computing. The tool uncovers…

Long short-term memory (LSTM) is one of the robust recurrent neural network architectures for learning sequential data. However, it requires considerable computational power to learn and implement both software and hardware aspects. This…

Much research effort is being applied to the task of compressing the knowledge of self-supervised models, which are powerful, yet large and memory consuming. In this work, we show that the original method of knowledge distillation (and its…

The paper presents a learned two-dimensional separable transform (LST) that can be considered as a new type of computational layer for constructing neural network (NN) architecture for image recognition tasks. The LST based on the idea of…

Recently, pre-trained Transformer based language models, such as BERT, have shown great superiority over the traditional methods in many Natural Language Processing (NLP) tasks. However, the computational cost for deploying these models is…

Transfer learning from pre-trained neural language models towards downstream tasks has been a predominant theme in NLP recently. Several researchers have shown that deep NLP models learn non-trivial amount of linguistic knowledge, captured…

BERT, which stands for Bidirectional Encoder Representations from Transformers, is a recently introduced language representation model based upon the transfer learning paradigm. We extend its fine-tuning procedure to address one of its…

Highly performing deep neural networks come at the cost of computational complexity that limits their practicality for deployment on portable devices. We propose the low-rank transformer (LRT), a memory-efficient and fast neural…

Transformer-based NLP models are trained using hundreds of millions or even billions of parameters, limiting their applicability in computationally constrained environments. While the number of parameters generally correlates with…