RESEARCH
SPEECH & AUDIO
Pay less attention with Lightweight and Dynamic Convolutions
April 19, 2019
Abstract
Self-attention is a useful mechanism to build generative models for language and images. It determines the importance of context elements by comparing each element to the current time step. In this paper, we show that a very lightweight convolution can perform competitively to the best reported self-attention results. Next, we introduce dynamic convolutions which are simpler and more efficient than self-attention. We predict separate convolution kernels based solely on the current time-step in order to determine the importance of context elements. The number of operations required by this approach scales linearly in the input length, whereas self-attention is quadratic. Experiments on large-scale machine translation, language modeling and abstractive summarization show that dynamic convolutions improve over strong self-attention models. On the WMT'14 English-German test set dynamic convolutions achieve a new state of the art of 29.7 BLEU.
AUTHORS
Publisher
ICLR
Related Publications
November 30, 2023
SPEECH & AUDIO
NLP
Efficient Monotonic Multihead Attention
Xutai Ma, Anna Sun, Hirofumi Inaguma, Paden Tomasello, Siqi Ouyang
November 30, 2023
November 30, 2023
SPEECH & AUDIO
NLP
Seamless: Multilingual Expressive and Streaming Speech Translation
Seamless Communication, Loïc Barrault, Yu-An Chung, Mariano Coria Meglioli, David Dale, Ning Dong, Mark Duppenthaler, Paul-Ambroise Duquenne, Brian Ellis, Hady Elsahar, Justin Haaheim, John Hoffman, Min-Jae Hwang, Hirofumi Inaguma, Christopher Klaiber, Ilia Kulikov, Pengwei Li, Daniel Licht, Jean Maillard, Ruslan Mavlyutov, Alice Rakotoarison, Kaushik Ram Sadagopan, Abinesh Ramakrishnan, Tuan Tran, Guillaume Wenzek, Yilin Yang, Ethan Ye, Ivan Evtimov, Pierre Fernandez, Cynthia Gao, Prangthip Hansanti, Elahe Kalbassi, Amanda Kallet, Artyom Kozhevnikov, Gabriel Mejia Gonzalez, Robin San Roman, Christophe Touret, Corinne Wong, Carleigh Wood, Bokai Yu, Pierre Andrews, Can Balioglu, Peng-Jen Chen, Marta R. Costa-jussà, Maha Elbayad, Hongyu Gong, Francisco Guzmán, Kevin Heffernan, Somya Jain, Justine Kao, Ann Lee, Xutai Ma, Alexandre Mourachko, Benjamin Peloquin, Juan Pino, Sravya Popuri, Christophe Ropers, Safiyyah Saleem, Holger Schwenk, Anna Sun, Paden Tomasello, Changhan Wang, Jeff Wang, Skyler Wang, Mary Williamson
November 30, 2023
October 04, 2023
HUMAN & MACHINE INTELLIGENCE
SPEECH & AUDIO
Decoding speech perception from non-invasive brain recordings
Alexandre Defossez, Charlotte Caucheteux, Jérémy Rapin, Ori Kabeli, Jean Remi King
October 04, 2023
August 22, 2023
SPEECH & AUDIO
NLP
SeamlessM4T—Massively Multilingual & Multimodal Machine Translation
Seamless Communication, Loic Barrault, Andy Chung, David Dale, Ning Dong (AI), Paul-Ambroise Duquenne, Hady Elsahar, Hongyu Gong, Kevin Heffernan, John Hoffman, Christopher Klaiber, Peng-Jen Chen, Daniel Licht, Jean Maillard, Alice Rakotoarison, Kaushik Ram Sadagopan, Guillaume Wenzek, Abinesh Ramakrishnan, Alexandre Mourachko, Amanda Kallet, Ann Lee, Anna Sun, Bapi Akula, Benjamin Peloquin, Bernie Huang, Bokai Yu, Brian Ellis, Can Balioglu, Carleigh Wood, Changhan Wang, Christophe Ropers, Cynthia Gao, Daniel Li (FAIR), Elahe Kalbassi, Ethan Ye, Gabriel Mejia Gonzalez, Hirofumi Inaguma, Holger Schwenk, Igor Tufanov, Ilia Kulikov, Janice Lam, Jeff Wang (PM - AI), Juan Pino, Justin Haaheim, Justine Kao, Prangthip Hasanti, Kevin Tran, Maha Elbayad, Marta R. Costa-jussa, Mohamed Ramadan, Naji El Hachem, Onur Çelebi, Paco Guzmán, Paden Tomasello, Pengwei Li, Pierre Andrews, Ruslan Mavlyutov, Russ Howes, Safiyyah Saleem, Skyler Wang, Somya Jain, Sravya Popuri, Tuan Tran, Vish Vogeti, Xutai Ma, Yilin Yang
August 22, 2023
Help Us Pioneer The Future of AI
We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.
Who We Are
Our Actions
Newsletter
Meta © 2023