Is ChatGPT a General-Purpose Natural Language Processing Task Solver? [PDF]
Conference on Empirical Methods in Natural Language Processing, 2023 Spurred by advancements in scale, large language models (LLMs) have demonstrated the ability to perform a variety of natural language processing (NLP) tasks zero-shot -- i.e., without adaptation on downstream data.
Chengwei Qin +5 more
openalex +3 more sources
WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing [PDF]
IEEE Journal on Selected Topics in Signal Processing, 2021 Self-supervised learning (SSL) achieves great success in speech recognition, while limited exploration has been attempted for other speech processing tasks.
Sanyuan Chen +16 more
semanticscholar +1 more source
In-datacenter performance analysis of a tensor processing unit [PDF]
International Symposium on Computer Architecture, 2017 Many architects believe that major improvements in cost-energy-performance must now come from domain-specific hardware. This paper evaluates a custom ASIC-called a Tensor Processing Unit (TPU)-deployed in datacenters since 2015 that accelerates the ...
Norman P. Jouppi +75 more
semanticscholar +1 more source
SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing [PDF]
Conference on Empirical Methods in Natural Language Processing, 2018 This paper describes SentencePiece, a language-independent subword tokenizer and detokenizer designed for Neural-based text processing, including Neural Machine Translation. It provides open-source C++ and Python implementations for subword units.
Taku Kudo, John Richardson
semanticscholar +1 more source
Efficient Processing of Deep Neural Networks: A Tutorial and Survey [PDF]
Proceedings of the IEEE, 2017 Deep neural networks (DNNs) are currently widely used for many artificial intelligence (AI) applications including computer vision, speech recognition, and robotics.
V. Sze +3 more
semanticscholar +1 more source
8th International Multitopic Conference, 2004. Proceedings of INMIC 2004., 2018 Convolutional neural networks (CNNs) have been widely used in medical imaging applications, including brain diseases such as Alzheimer’s disease (AD) classification based on neuroimaging data.
Thomas J. Cavicchi, U. Spagnolini
semanticscholar +1 more source
The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains [PDF]
IEEE Signal Processing Magazine, 2012 In applications such as social, energy, transportation, sensor, and neuronal networks, high-dimensional data naturally reside on the vertices of weighted graphs.
D. Shuman +4 more
semanticscholar +1 more source
Pre-Trained Image Processing Transformer [PDF]
Computer Vision and Pattern Recognition, 2020 As the computing power of modern hardware is increasing strongly, pre-trained deep learning models (e.g., BERT, GPT-3) learned on large-scale datasets have shown their effectiveness over conventional methods. The big progress is mainly contributed to the
Hanting Chen +9 more
semanticscholar +1 more source
The relationship between reading working memory and reading comprehension of Iranian second-cycle high school students from a psycho-linguistic viewpoint [PDF]
فصلنامه نوآوریهای آموزشی, 2019 This mixed-methods research studies the relationship between reading working memory and reading comprehension among high school students from a psycho-linguistic view.
Maryam Dānāye Tous +2 more
doaj +1 more source
Applications of cellulose nanomaterials in pharmaceutical science and pharmacology
eXPRESS Polymer Letters, 2018 Cellulose nanomaterials (CNs) have been successfully applied to a variety of scientific areas in recent years with remarkable engineering utilities.
Y. Cao
doaj +1 more source