Papers by Ashish Vaswani
Self-Attention with Relative Position Representations (N18-2)
Copied to clipboard
| Challenge: | Recent approaches to sequence to sequence learning leverage recurrence, convolution, attention or combination of recurrent and convolutional neural networks. |
| Approach: | They propose an approach that extends the self-attention mechanism to consider representations of relative positions, or distances between sequence elements. |
| Outcome: | The proposed approach yields 1.3 BLEU and 0.3 BLUE on translation tasks . it is based on a relation-aware self-attention mechanism that can generalize to arbitrary graph-labeled inputs. |
The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation (P18-1)
Copied to clipboard
Mia Xu Chen, Orhan Firat, Ankur Bapna, Melvin Johnson, Wolfgang Macherey, George Foster, Llion Jones, Mike Schuster, Noam Shazeer, Niki Parmar, Ashish Vaswani, Jakob Uszkoreit, Lukasz Kaiser, Zhifeng Chen, Yonghui Wu, Macduff Hughes
| Challenge: | In recent years, the emergence of seq2seq models has revolutionized the field of machine translation by replacing traditional phrase-based approaches with neural machine translation (NMT) systems based on the encoder-decoder paradigm. |
| Approach: | They propose to use a convolutional seq2seq model to combine the strengths of the two approaches. |
| Outcome: | The proposed architectures outperform the existing models on the WMT’14 benchmark dataset. |
Stay on the Path: Instruction Fidelity in Vision-and-Language Navigation (P19-1)
Copied to clipboard
| Challenge: | Existing metrics for vision-and-language navigation focus on goal completion rather than the sequence of actions corresponding to the instructions. |
| Approach: | They propose to use a room-to-room dataset to measure the length of instruction followed by agents. |
| Outcome: | The proposed metric outperforms existing metrics for Room-to-Room tasks because it is direct-to goal shortest. |
Efficient Content-Based Sparse Attention with Routing Transformers (2021.tacl-1)
Copied to clipboard
| Challenge: | Self-attention suffers from quadratic computation and memory requirements with respect to sequence length . despite its effectiveness, self-attention models suffer from quadratic computation and a limited set of locations . |
| Approach: | They propose to learn dynamic sparse attention patterns that avoid allocating computation and memory to attend to content unrelated to the query of interest. |
| Outcome: | The proposed model outperforms similar sparse attention models on language modeling and image generation on Wikitext-103 . |