Papers by Ashish Vaswani

4 papers
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

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 .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations