An embarrassingly simple method to mitigate undesirable properties of pretrained language model tokenizers (2022)

First Author: Hofmann V
Attributed to:  Exaggeration, cohesion, and fragmentation in on-line forums funded by EPSRC

Abstract

No abstract provided

Bibliographic Information

Publication URI: https://aclanthology.org/2022.acl-short.43.pdf

Type: Conference/Paper/Proceeding/Abstract

Volume: 60