Dialogue data in real scenarios tend to be sparsely available, rendering...
As the functionality of dialogue systems evolves, hybrid dialogue system...
Task-Oriented Dialogue (TOD) systems are drawing more and more attention...
Adversarial attacks can mislead strong neural models; as such, in NLP ta...
We present a Chinese BERT model dubbed MarkBERT that uses word informati...
Whole word masking (WWM), which masks all subwords corresponding to a wo...
Pre-trained models are widely used in fine-tuning downstream tasks with
...
Pre-Trained Models have been widely
applied and recently proved vulnerab...
Recent studies have shown that deep neural networks are vulnerable to
in...
Distant supervision for relation extraction provides uniform bag labels ...
Recently, few certified defense methods have been developed to provably
...
Adversarial attacks in texts are mostly substitution-based methods that
...
Adversarial training is effective in improving the robustness of neural
...
Adversarial attacks for discrete data (such as text) has been proved
sig...
Machine reading comprehension with unanswerable questions is a new
chall...