Recent work in natural language processing (NLP) has yielded appealing results from
scaling model parameters and training data; however, using only scale to improve …

Adaptive training approaches, widely used in sequence-to-sequence models, commonly
reweigh the losses of different target tokens based on priors, eg word frequency. However …

Cells/nuclei deliver massive information of microenvironment. An automatic nuclei
segmentation approach can reduce pathologists' workload and allow precise of the …

State-of-the-art classification and regression models are often not well calibrated, and
cannot reliably provide uncertainty estimates, limiting their utility in safety-critical …

Low-frequency word prediction remains a challenge in modern neural machine translation
(NMT) systems. Recent adaptive training methods promote the output of infrequent words by …

Short texts (STs) present in a variety of scenarios, including query, dialog, and entity names.
Most of the exciting studies in neural machine translation (NMT) are focused on tackling …

Curriculum learning, a machine training strategy that feeds training instances to the model
from easy to hard, has been proven to facilitate the dialogue generation task. Meanwhile …

Artificial neural networks have shown promising results in a variety of natural language
understanding (NLU) tasks. Despite their successes, conventional neural-based NLU …

Simultaneous Machine Translation (SiMT) generates target outputs while receiving stream
source inputs and requires a read/write policy to decide whether to wait for the next source …