Augmenting Transformers with KNN-Based Composite Memory for Dialogue

Fan Angela
Fan Angela
Gardent Claire
Gardent Claire
Braud Chloe
Braud Chloe
Cited by: 0|Bibtex|Views66
Other Links: arxiv.org

Abstract:

Various machine learning tasks can benefit from access to external information of different modalities, such as text and images. Recent work has focused on learning architectures with large memories capable of storing this knowledge. We propose augmenting generative Transformer neural networks with KNN-based Information Fetching (KIF) m...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments