mirror of
https://github.com/facebookresearch/fairseq.git
synced 2024-09-11 09:15:43 +03:00
Fix typo
This commit is contained in:
parent
5b87224417
commit
c83960a2db
@ -4,7 +4,7 @@
|
||||
|
||||
## Introduction
|
||||
|
||||
BART is sequence-to-sequence model trained with denoising as pretraining objective. We show that this pretraining objective is more generic and show that we can match [RoBERTa](../roberta) results on SQuAD and GLUE and gain state-of-the-art results on summarization (XSum, CNN dataset), long form generative question answering (ELI5) and dialog response genration (ConvAI2). See the associated paper for more details.
|
||||
BART is sequence-to-sequence model trained with denoising as pretraining objective. We show that this pretraining objective is more generic and show that we can match [RoBERTa](../roberta) results on SQuAD and GLUE and gain state-of-the-art results on summarization (XSum, CNN dataset), long form generative question answering (ELI5) and dialog response generation (ConvAI2). See the associated paper for more details.
|
||||
|
||||
## Pre-trained models
|
||||
|
||||
|
Loading…
Reference in New Issue
Block a user