Loading...
Provable Limitations of Acquiring Meaning from Ungrounded Form: What Will Future Language Models Understand?
AbstractLanguage models trained on billions of tokens have recently led to unprecedented results on many NLP tasks. This success raises the question of whether, in principle, a system can ever “understand” raw text without access to some form of grounding. We formally investigate the...
Na minha lista:
| Main Authors: | , , , |
|---|---|
| Format: | Artigo |
| Sprog: | Inglês |
| Udgivet: |
The MIT Press
2021-01-01
|
| Serier: | Transactions of the Association for Computational Linguistics |
| Online adgang: | https://direct.mit.edu/tacl/article/doi/10.1162/tacl_a_00412/107385/Provable-Limitations-of-Acquiring-Meaning-from |
| Tags: |
Tilføj Tag
Ingen Tags, Vær først til at tagge denne postø!
|