activity
20182022
most citedRoot Mean Square Layer Normalization

106 citations · 139 across the 7 of their papers we have counts for

collaborators

14 papers

cs.CL20222 cited

Examining Scaling and Transfer of Language Model Architectures for Machine Translation

Biao Zhang, Behrooz Ghorbani, Ankur Bapna +4

Natural language understanding and generation models follow one of the two dominant architectural paradigms: language models (LMs) that process concatenated sequences in a single s…

cs.LG20228 cited

Data Scaling Laws in NMT: The Effect of Noise and Architecture

Yamini Bansal, Behrooz Ghorbani, Ankush Garg +5

In this work, we study the effect of varying the architecture and training data quality on the data scaling properties of Neural Machine Translation (NMT). First, we establish that…

cs.CL2021

Sparse Attention with Linear Units

Biao Zhang, Ivan Titov, Rico Sennrich

Recently, it has been argued that encoder-decoder models can be made more interpretable by replacing the softmax function in the attention with its sparse variants. In this work, w…

cs.CL20204 cited

Fast Interleaved Bidirectional Sequence Generation

Biao Zhang, Ivan Titov, Rico Sennrich

Independence assumptions during sequence generation can speed up inference, but parallel generation of highly inter-dependent tokens comes at a cost in quality. Instead of assuming…

cs.CL2020

Adaptive Feature Selection for End-to-End Speech Translation

Biao Zhang, Ivan Titov, Barry Haddow +1

Information in speech signals is not evenly distributed, making it an additional challenge for end-to-end (E2E) speech translation (ST) to learn to focus on informative features. I…

cs.CL20207 cited

On Sparsifying Encoder Outputs in Sequence-to-Sequence Models

Biao Zhang, Ivan Titov, Rico Sennrich

Sequence-to-sequence models usually transfer all encoder outputs to the decoder for generation. In this work, by contrast, we hypothesize that these encoder outputs can be compress…