5 accepted papers
The process of designing neural architectures requires expert knowledge and extensive trial and error. While automated architecture search may simplify these requirements, the recurrent neural network (RNN) architectures generated by existing methods are limited in both flexibility and components. W…
In this paper, we consider the specific problem of word-level language modeling and investigate strategies for regularizing and optimizing LSTM-based models. We propose the weight-dropped LSTM, which uses DropConnect on hidden-to-hidden weights, as a form of recurrent regularization. Further, we int…
Recent neural network sequence models with softmax classifiers have achieved their best language modeling performance only with very large hidden states and large vocabularies. Even then they struggle to predict rare or unseen words even if the context makes the prediction unambiguous. We introduce…
Recurrent neural networks are a powerful tool for modeling sequential data, but the dependence of each timestep’s computation on the previous timestep’s output limits parallelism and makes RNNs unwieldy for very long sequences. We introduce quasi-recurrent neural networks (QRNNs), an approach to neu…
Neural network architectures with memory and attention mechanisms exhibit certain reason- ing capabilities required for question answering. One such architecture, the dynamic memory net- work (DMN), obtained high accuracy on a variety of language tasks. However, it was not shown whether the architec…