In simultaneous translation (SimulMT), the most widely used strategy is ...
There are so many models in the literature that it is difficult for
prac...
This paper compares BERT-SQuAD and Ab3P on the Abbreviation Definition
I...
In this work, we propose DiffWave, a versatile Diffusion probabilistic m...
Scaling up the vocabulary and complexity of current visual understanding...
We show how Zipf's Law can be used to scale up language modeling (LM) to...
We propose a large margin criterion for training neural language models....
We propose a Topic Compositional Neural Language Model (TCNLM), a novel
...
Deep neural networks have proved very successful on archetypal tasks for...
Replacing hand-engineered pipelines with end-to-end deep learning system...
In training speech recognition systems, labeling audio clips can be
expe...
Deep neural networks have proved very successful in domains where large
...
This paper describes a novel approach to change-point detection when the...