Papers by Janet Wiles

1 papers
A Systematic Study Reveals Unexpected Interactions in Pre-Trained Neural Machine Translation (2022.lrec-1)

Copied to clipboard

Challenge: Transfer learning is a promising direction for low-resource neural machine translation (NMT) but it introduces many new variables which are often selected through ablation studies, costly trial-and-error, or niche expertise.
Approach: They conducted a three-factor experiment to examine how language similarity, pre-training dataset size and main dataset size interacted in their effect on performance in pre-trained transformer-based low-resource NMT.
Outcome: The results suggest that systematic studies of interactions may be a promising long-term direction for guiding research in low-resource neural machine translation.

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