In this work, we propose a new and general framework to defend against
b...
Backdoor attacks pose a new threat to NLP models. A standard strategy to...
Pre-trained Natural Language Processing (NLP) models can be easily adapt...
In this paper, we propose a new paradigm for paraphrase generation by
tr...
A long-standing issue with paraphrase generation is how to obtain reliab...
Out-of-Distribution (OOD) detection is an important problem in natural
l...
The proposed pruning strategy offers merits over weight-based pruning
te...
The frustratingly fragile nature of neural network models make current
n...
The standard way to estimate the parameters Θ_SEIR (e.g., the
transmissi...
Higher-order methods for dependency parsing can partially but not fully
...
Existing methods to measure sentence similarity are faced with two
chall...
Existing approaches to explaining deep learning models in NLP usually su...
The goal of semi-supervised learning is to utilize the unlabeled, in-dom...
Long-text generation remains a challenge. The difficulty of generating
c...