Intent classification (IC) plays an important role in task-oriented dial...
Conventional text style transfer approaches for natural language focus o...
When upgrading neural models to a newer version, new errors that were no...
Backward compatibility of model predictions is a desired property when
u...
Functionality and dialogue experience are two important factors of
task-...
In text classification tasks, useful information is encoded in the label...
Recent advance in deep learning has led to rapid adoption of machine lea...
Pre-trained language models have been recently shown to benefit task-ori...
We introduce a Recursive INsertion-based Encoder (RINE), a novel approac...
In this paper, we offer a preliminary investigation into the task of in-...
Neural machine translation (NMT) has arguably achieved human level parit...
Undirected neural sequence models such as BERT have received renewed int...
A molecule's geometry, also known as conformation, is one of a molecule'...
We propose a conditional non-autoregressive neural sequence model based ...
In this work, we propose to apply trust region optimization to deep
rein...
Motivated by the recent progress in generative models, we introduce a mo...
We propose a new way of incorporating temporal information present in vi...
We use multilayer Long Short Term Memory (LSTM) networks to learn
repres...