Although with progress in introducing auxiliary amortized inference models, learning discrete latent variable models is still challenging.
Annotating datasets is one of the main costs in nowadays supervised learning.
We present MT-DNN, an open-source natural language understanding (NLU) toolkit that makes it easy for researchers and developers to train customized deep learning models.
We derive an unbiased estimator for expectations over discrete random variables based on sampling without replacement, which reduces variance as it avoids duplicate samples.
The literature on structured prediction for NLP describes a rich collection of distributions and algorithms over sequences, segmentations, alignments, and trees; however, these algorithms are difficult to utilize in deep learning frameworks.
One of the keys to enable chatbots to communicate with human in a more natural way is the ability to handle long and complex user's utterances.
Structured prediction requires manipulating a large number of combinatorial structures, e. g., dependency trees or alignments, either as latent or output variables.
While centralized reinforcement learning methods can optimally solve small MAC instances, they do not scale to large problems and they fail to generalize to scenarios different from those seen during training.