Multi-task learning (MTL) aims at enhancing the performance and efficien...
Although recent works have developed methods that can generate estimatio...
Voice style transfer, also called voice conversion, seeks to modify one
...
Pretrained text encoders, such as BERT, have been applied increasingly i...
Cross-domain alignment between image objects and text sequences is key t...
We present a syntax-infused variational autoencoder (SIVAE), that integr...