Papers with adaptive and layer-wise domain mixing

1 papers
Multi-Domain Neural Machine Translation with Word-Level Adaptive Layer-wise Domain Mixing (2020.acl-main)

Copied to clipboard

Challenge: Existing multi-domain neural machine translation models lack adaptation to individual domains.
Approach: They propose a multi-domain neural machine translation model with individual modules for each domain . they use word-level, adaptive and layer-wise domain mixing to achieve this .
Outcome: The proposed model outperforms existing models in several NMT tasks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations