Ashish Vaswani
- Publications
- Influence
Claim Your Author Page
Ensure your research is discoverable on Semantic Scholar. Claiming your author page allows you to personalize the information displayed and manage your publications. Semantic Scholar automatically creates author pages based on data aggregated from public sources and our publisher partners.
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… Expand
Artificial intelligence (AI) has undergone a renaissance recently, making major progress in key domains such as vision, language, control, and decision-making. This has been due, in part, to cheap… Expand
Relying entirely on an attention mechanism, the Transformer introduced by Vaswani et al. (2017) achieves state-of-the-art results for machine translation. In contrast to recurrent and convolutional… Expand
We explore the application of neural language models to machine translation. We develop a new model that combines the neural probabilistic language model of Bengio et al., rectified linear units, and… Expand
Non-expert annotation services like Amazon’s Mechanical Turk (AMT) are cheap and fast ways to evaluate systems and provide categorical annotations for training data. Unfortunately, some annotators… Expand
Tensor2Tensor is a library for deep learning models that is well-suited for neural machine translation and includes the reference implementation of the state-of-the-art Transformer model.
IEEE/CVF International Conference on Computer…
Convolutional networks have enjoyed much success in many computer vision applications. The convolution operation however has a significant weakness in that it only operates on a local neighbourhood,… Expand
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… Expand
In this paper we present new state-of-the-art performance on CCG supertagging and parsing. Our model outperforms existing approaches by an absolute gain of 1.5%. We analyze the performance of several… Expand
Autoregressive sequence models based on deep neural networks, such as RNNs, Wavenet and the Transformer attain state-of-the-art results on many tasks. However, they are difficult to parallelize and… Expand