Adapter 与 Prompt Tuning 微调方法研究综述.
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3AVSFJJTCL" target="_blank" >RIV/00216208:11320/23:VSFJJTCL - isvavai.cz</a>
Result on the web
<a href="http://cea.ceaj.org/CN/Y2023/V59/I2/12" target="_blank" >http://cea.ceaj.org/CN/Y2023/V59/I2/12</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.3778/j.issn.1002-8331.2209-0025" target="_blank" >10.3778/j.issn.1002-8331.2209-0025</a>
Alternative languages
Result language
chorvatština
Original language name
Adapter 与 Prompt Tuning 微调方法研究综述.
Original language description
"Text mining is a branch of data mining, covering a variety of technologies, among which natural language processing technology is one of the core tools of text mining, which aims to help users obtain useful information from massive data. In recent years, the pre-training model has played an important role in promoting the research and development of natural language processing, and the fine-tuning method of the pre-training model has also become an important research field. On the basis of the relevant literature on the pre-training model fine-tuning method published in recent years, this paper reviews the current mainstream Adapter and Prompt methods. First of all, the development of natural language processing is briefly combed, and the problems and difficulties in fine-tuning of pre-training models are analyzed. Secondly, two kinds of fine-tuning methods: Adapter and Prompt, and the classic methods in the this two research directions are introduced. The advantages, disadvantages and performance are analyzed and summarized. Finally, this paper summarizes the limitations of the current fine-tuning methods of the pre-training model and discusses the future development direction."
Czech name
—
Czech description
—
Classification
Type
J<sub>ost</sub> - Miscellaneous article in a specialist periodical
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
—
Others
Publication year
2023
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Name of the periodical
"Journal of Computer Engineering & Applications"
ISSN
1002-8331
e-ISSN
—
Volume of the periodical
59
Issue of the periodical within the volume
2
Country of publishing house
HR - CROATIA
Number of pages
10
Pages from-to
12-21
UT code for WoS article
—
EID of the result in the Scopus database
—