Berlin

The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely....

Recent work demonstrated significant progress towards modeling the distribution of natural images with tractable likelihood using deep neural networks. This was achieved by modeling the joint distribution of pixels in the image as the product of conditional distributions, thereby turning it into a sequence modeling problem, and applying recurrent or convolutional neural networks to it. In this...

Auto-regressive sequence models based on deep neural networks, such as RNNs, Wavenet and Transformer are the state of the art on many tasks. However, they lack parallelism and are thus slow for long sequences. RNNs lack parallelism both during training and decoding, while architectures like WaveNet and Transformer are much more parallel during training, but still lack parallelism during...

We present a solution to the problem of paraphrase identification of questions. We focus on a recent dataset of question pairs annotated with binary paraphrase labels and show that a variant of the decomposable attention model (Parikh et al., 2016) results in accurate performance on this task, while being far simpler than many competing neural architectures. Furthermore, when the model is...

Recent advances in generative modeling have led to an increased interest in the study of statistical divergences as means of model comparison. Commonly used evaluation methods, such as Fr\'echet Inception Distance (FID), correlate well with the perceived quality of samples and are sensitive to mode dropping. However, these metrics are unable to distinguish between different failure cases since...

A state-of-the-art, commercial speech recognition system should not only have a low word error rate (WER), but must also abide by latency constraints. % Specifically, the model must be decode utterances in a streaming fashion and faster than real-time. % Recently, a streaming recurrent neural network transducer (RNN-T) end-to-end (E2E) model has shown to be a good candidate for on-device speech...

In conventional speech recognition, phoneme-based models outperform grapheme-based models for non-phonetic languages such as English. The performance gap between the two typically reduces as the amount of training data is increased. In this work, we examine the impact of the choice of modeling unit for attention-based encoder-decoder models. We conduct experiments on the LibriSpeech 100hr,...

The goal of this paper is to design image classification systems that, after an initial multi-task training phase, can automatically adapt to new tasks encountered at test time. We introduce a conditional neural process based approach to the multi-task classification setting for this purpose, and establish connections to the meta- and few-shot learning literature. The resulting approach, called...

Music relies heavily on repetition to build structure and meaning. Self-reference occurs on multiple timescales, from motifs to phrases to reusing of entire sections of music, such as in pieces with ABA structure. The Transformer (Vaswani et al., 2017), a sequence model based on self-attention, has achieved compelling results in many generation tasks that require maintaining long-range...

Recurrent neural networks (RNNs) sequentially process data by updating their state with each new data point, and have long been the de facto choice for sequence modeling tasks. However, their inherently sequential computation makes them slow to train. Feed-forward and convolutional architectures have recently been shown to achieve superior results on some sequence modeling tasks such as machine...

Due to the statistical complexity of video, the high degree of inherent stochasticity, and the sheer amount of data, generating natural video remains a challenging task. State-of-the-art video generation models attempt to address these issues by combining sometimes complex, often video-specific neural network architectures, latent variable models, adversarial training and a range of other...

In this paper we study various flavors of variational autoencoders and address the methodological issues with the current neural text generation research and also close some gaps by answering a few natural questions to the studies already published.