Skip to content

Investigate the emergence of factual knowledge in Pretrained Multilingual Language Models. For this we explore factual knowledge sharing and symbolic reasoning in a zero-shot cross-lingual setting.

Notifications You must be signed in to change notification settings

laurinpaech/emergence-factual-knowledge

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Emergence of Factual Knowledge in Pretrained Multilingual Language Models

We investigate the emergence of factual knowledge in pretrained MLLMs. More concretely, we conduct a study to explore factual knowledge sharing and symbolic reasoning in a zero-shot cross-lingual setting. For this we investigate (i) how much these models depend on a shared representation when being probed for factual knowledge and (ii) the ability to use symbolic reasoning across languages to infer factual knowledge not seen explicitly during pretraining.

Getting started

To run the experiments we provide several bash scripts with already pre-selected hyperparameters.

About

Investigate the emergence of factual knowledge in Pretrained Multilingual Language Models. For this we explore factual knowledge sharing and symbolic reasoning in a zero-shot cross-lingual setting.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published