Recent development in vision-language approaches has instigated a paradi...
Pretrained model-based evaluation metrics have demonstrated strong
perfo...
Vision-and-language navigation (VLN) agents are trained to navigate in
r...
We present X-Decoder, a generalized decoding model that can predict
pixe...
Vision-language (VL) pre-training has recently received considerable
att...
The speaker-follower models have proven to be effective in
vision-and-la...
Commonsense question answering (CQA) aims to test if models can answer
q...
Vision-and-language (VL) pre-training has proven to be highly effective ...
Although some recent works show potential complementarity among differen...
Word alignment over parallel corpora has a wide variety of applications,...
Neural abstractive summarization models are flexible and can produce coh...
Neural network-based models augmented with unsupervised pre-trained know...
The COVID-19 pandemic is the worst pandemic to strike the world in over ...
Back-translation has proven to be an effective method to utilize monolin...
Neural networks are known to be data hungry and domain sensitive, but it...
The recent success of neural machine translation models relies on the
av...
Learning general representations of text is a fundamental problem for ma...
Multi-head attention is appealing for its ability to jointly extract
dif...
In this paper, we describe compare-mt, a tool for holistic analysis and
...
With the promising progress of deep neural networks, layer aggregation h...
Advanced neural machine translation (NMT) models generally implement enc...
Increasing depth and complexity in convolutional neural networks has ena...
The past several years have witnessed the rapid progress of end-to-end N...