Robust Question Answering Through Sub-part Alignment

Chen Jifan
Chen Jifan
Cited by: 0|Bibtex|Views10
Other Links: arxiv.org

Abstract:

Current textual question answering models achieve strong performance on in-domain test sets, but often do so by fitting surface-level patterns in the data, so they fail to generalize to out-of-distribution and adversarial settings. To make a more robust and understandable QA system, we model question answering as an alignment problem. W...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments