2024
Natural language processing with transformers: a review
Abstract: Natural language processing (NLP) tasks can be addressed with several deep learning architectures, and many different approaches have proven to be efficient. This study aims to briefly summarize the use cases for NLP tasks along with the main architectures. This research presents transformer-based solutions for NLP tasks such as Bidirectional Encoder Representations from Transformers (BERT), and Generative Pre-Training (GPT) architectures. To achieve that, we conducted a step-by-step process in the review stra…
Search citation statements
Paper Sections
Select...
59
1
1
1
Citation Types
0
4
0
0
Year Published
2006
2026
Publication Types
Select...
49
10
3
Relationship
0
62
Authors
Journals
Cited by 17 publications
(4 citation statements)
References 51 publications
0
4
0
0
“…The real-time conditions and hardware specifications should be considered ( Alderson-Day and Fernyhough, 2015 ; Angrick et al, 2019 ). In the future, it would be interesting to investigate lightweight Transformer architectures or hardware accelerators (e.g., FPGA/edge AI devices) to enable deployment without accuracy compromise ( Birbaumer et al, 2008 ; Tucudean et al, 2024 ).…”
Section: Discussionmentioning
confidence: 99%
“…The real-time conditions and hardware specifications should be considered ( Alderson-Day and Fernyhough, 2015 ; Angrick et al, 2019 ). In the future, it would be interesting to investigate lightweight Transformer architectures or hardware accelerators (e.g., FPGA/edge AI devices) to enable deployment without accuracy compromise ( Birbaumer et al, 2008 ; Tucudean et al, 2024 ).…”
Section: Discussionmentioning
confidence: 99%
“…BERT is a Transformer-based technique for pre-training contextual word representations that enables state-of-the-art results across a wide range of NLP tasks ( 49 , 50 ). It includes two separate stages, pre-training and fine-tuning, which may develop general understandings from massive amounts of unlabeled data and then solve various applications with minimal task-specific architectural changes.…”
Section: Methodsmentioning
confidence: 99%
“…This capability makes transformers highly valuable in the development of personalized treatment plans and cancer prognosis assessment. Furthermore, transformers are revolutionizing various fields, particularly in generative tasks and reinforcement learning, due to their ability to model intricate patterns and relationships within data [ 73 ]. Transformers have demonstrated remarkable effectiveness and scalability, paving the way for next‐generation models that could provide deeper insights across various domains [ 74 ].…”
Section: Ai Foundations For Oncology: Beyond Algorithmsmentioning
confidence: 99%
