Open-domain dialogue systems aim to interact with humans through natural...
Semantic parsing datasets are expensive to collect. Moreover, even the
q...
A natural language database interface (NLDB) can democratize data-driven...
In this paper, we propose a globally normalized model for context-free
g...
Semantic parsing is the task of converting natural language utterances t...
Due to the common belief that training deep transformers from scratch
re...
The field of deep generative modeling has succeeded in producing
astonis...
In this work, we propose a novel probabilistic sequence model that excel...
Variational Autoencoders (VAEs) hold great potential for modelling text,...
In this work, we develop a novel regularizer to improve the learning of
...
Existing controllable text generation systems rely on annotated attribut...
Coherence is an important aspect of text quality and is crucial for ensu...
Deep neural networks are known to suffer the catastrophic forgetting pro...
We propose a novel regularizer to improve the training of Generative
Adv...
Learning by contrasting positive and negative samples is a general strat...
This paper raises an implicit manifold learning perspective in Generativ...
t-Distributed Stochastic Neighbor Embedding (t-SNE) is one of the most w...
We introduce a framework for analyzing transductive combination of Gauss...
We show that the representation of an image in a deep neural network (DN...
In this work, we propose a generalized product of experts (gPoE) framewo...