New meaning for NLP: the trials and tribulations of natural language processing with GPT-3 in ophthalmology

Natural language processing (NLP) is a subfield of machine intelligence focused on the interaction of human language with computer systems. NLP has recently been discussed in the mainstream media and the literature with the advent of Generative Pre-trained Transformer 3 (GPT-3), a language model cap...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:British journal of ophthalmology Ročník 106; číslo 7; s. 889 - 892
Hlavní autoři: Nath, Siddharth, Marie, Abdullah, Ellershaw, Simon, Korot, Edward, Keane, Pearse A
Médium: Journal Article
Jazyk:angličtina
Vydáno: BMA House, Tavistock Square, London, WC1H 9JR BMJ Publishing Group Ltd 01.07.2022
BMJ Publishing Group LTD
Témata:
Cataracts
Datasets
Diagnostic tests/Investigation
Electronic health records
Gender
Humans
Internet
Language instruction
Medical diagnosis
Medical personnel
Medical research
Natural Language Processing
Ophthalmology
Pain management
Patients
Review
Telemedicine
Telemedicine
Diagnostic tests/Investigation
ISSN:0007-1161, 1468-2079, 1468-2079
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Natural language processing (NLP) is a subfield of machine intelligence focused on the interaction of human language with computer systems. NLP has recently been discussed in the mainstream media and the literature with the advent of Generative Pre-trained Transformer 3 (GPT-3), a language model capable of producing human-like text. The release of GPT-3 has also sparked renewed interest on the applicability of NLP to contemporary healthcare problems. This article provides an overview of NLP models, with a focus on GPT-3, as well as discussion of applications specific to ophthalmology. We also outline the limitations of GPT-3 and the challenges with its integration into routine ophthalmic care.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ObjectType-Review-3
content type line 23
ISSN:0007-1161
1468-2079
1468-2079
DOI:10.1136/bjophthalmol-2022-321141