29 citations · 123 across the 37 of their papers we have counts for
4 papers · 1 filter
Parameter Reference Loss for Unsupervised Domain Adaptation
Jiren Jin, Richard G. Calland, Takeru Miyato +2
The success of deep learning in computer vision is mainly attributed to an abundance of data. However, collecting large-scale data is not always possible, especially for the superv…
Compressing Word Embeddings via Deep Compositional Code Learning
Raphael Shu, Hideki Nakayama
Natural language processing (NLP) models often require a massive number of parameters for word embeddings, resulting in a large storage or memory footprint. Deploying neural NLP mo…
Single-Queue Decoding for Neural Machine Translation
Raphael Shu, Hideki Nakayama
Neural machine translation models rely on the beam search algorithm for decoding. In practice, we found that the quality of hypotheses in the search space is negatively affected ow…
Later-stage Minimum Bayes-Risk Decoding for Neural Machine Translation
Raphael Shu, Hideki Nakayama
For extended periods of time, sequence generation models rely on beam search algorithm to generate output sequence. However, the correctness of beam search degrades when the a mode…