In recent years, there has been significant progress in developing
pre-t...
Learning to search is the task of building artificial agents that learn ...
This paper presents a simple recipe to train state-of-the-art multilingu...
Professional summaries are written with document-level information, such...
We propose Masker, an unsupervised text-editing method for style transfe...
We evaluate the performance of transformer encoders with various decoder...
We propose LaserTagger - a sequence tagging approach that casts text
gen...
Unsupervised pre-training of large neural models has recently revolution...
Motivated by recent findings on the probabilistic modeling of acceptabil...
In this paper, we propose a method for training neural networks when we ...
Training deep neural networks requires massive amounts of training data,...
Users try to articulate their complex information needs during search
se...
Embeddings are generic representations that are useful for many NLP task...
We present AutoExtend, a system to learn embeddings for synsets and
lexe...