RobertCsordas/transformer_generalization
The official repository for our paper "The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers". We significantly improve the systematic generalization of transformer models on a variety of datasets using simple tricks and careful considerations.
PythonMIT
Stargazers
- lahwran
- zzw-zwzhang
- anirbanl
- hlzhang109Cambridge, MA
- jianjieluoGuangzhou, China
- diggerdu
- ankurshx
- flotothemoonZürich, Switzerland
- jbdatascienceNetherlands
- Kaffaljidhmah2
- 41xuTrento, Italy
- danny911krLos Angeles
- PtrMan
- liqing-ustcBeijing
- Hiroki11xMontreal, QC, Canada
- NarasimmanSaravana1994Chennai,Tamil Nadu,India
- danielz02Cambridge, MA
- avi-otteraiLos Angeles
- cctien
- u-tony-wuDuke University
- annaproxy
- Ci-TJ
- hwnam831
- mValentino91
- JeffCarpenterCanada
- evanatyourserviceDenver, CO
- robert1003
- ospanbatyrThe University of Edinburgh
- ahedalboodyNice-France
- Ryan0v0