Extending Input Contexts of Language Models through Training on Segmented Sequences

Extending Input Contexts of Language Models through Training on Segmented Sequences Petros Karypis author Julian McAuley author George Karypis author 2024-06 text Findings of the Association for Computational Linguistics: NAACL 2024 Kevin Duh editor Helena Gomez editor Steven Bethard editor Association for Computational Linguistics Mexico City, Mexico conference publication karypis-etal-2024-extending 10.18653/v1/2024.findings-naacl.191 https://aclanthology.org/2024.findings-naacl.191/ 2024-06 3040 3052