Many machine translation toolkits make use of a data preparation step wh...
We release MMSMR, a Massively Multi-System MultiReference dataset to ena...
Neural Machine Translation (NMT) models are known to suffer from noisy
i...
Non-task-oriented dialog models suffer from poor quality and non-diverse...
We consider the intrinsic evaluation of neural generative dialog models
...
Many valid translations exist for a given sentence, and yet machine
tran...
Machine translation systems based on deep neural networks are expensive ...
To better understand the effectiveness of continued training, we analyze...
We examine how various types of noise in the parallel training data impa...
The generation of complex derived word forms has been an overlooked prob...
We present Deep Generalized Canonical Correlation Analysis (DGCCA) -- a
...