Au sujet de ce document
- sl:arxiv_author :
- sl:arxiv_firstAuthor : Marcos Treviso
- sl:arxiv_num : 2209.00099
- sl:arxiv_published : 2022-08-31T20:32:35Z
- sl:arxiv_summary : Getting the most out of limited resources allows advances in natural language
processing (NLP) research and practice while being conservative with resources.
Those resources may be data, time, storage, or energy. Recent work in NLP has
yielded interesting results from scaling; however, using only scale to improve
results means that resource consumption also scales. That relationship
motivates research into efficient methods that require less resources to
achieve similar results. This survey relates and synthesises methods and
findings in those efficiencies in NLP, aiming to guide new researchers in the
field and inspire the development of new methods.@en
- sl:arxiv_title : Efficient Methods for Natural Language Processing: A Survey@en
- sl:arxiv_updated : 2022-08-31T20:32:35Z
- sl:bookmarkOf : https://arxiv.org/abs/2209.00099
- sl:creationDate : 2022-09-04
- sl:creationTime : 2022-09-04T11:26:48Z
Documents with similar tags (experimental)
Préférences...