Jongyoon Song

Building a Neural Machine Translation System Using Only Synthetic Parallel Data

2017 · arXiv (Cornell University)

Recent works have shown that synthetic parallel data automatically generated by translation models can be effective for various neural machine translation (NMT) issues. In this study, we build NMT systems using only synthetic parallel data. …

Rare Words Degenerate All Words.

2021 · arXiv (Cornell University)

Despite advances in neural network language model, the representation degeneration problem of embeddings is still challenging. Recent studies have found that the learned output embeddings are degenerated into a narrow-cone distribution which makes the similarity …