BlackOut: Speeding up Recurrent Neural Network Language Models With Very Large Vocabularies

21 November 2015

Papers citing "BlackOut: Speeding up Recurrent Neural Network Language Models With Very Large Vocabularies"

8 / 8 papers shown

Title
A Deep Learning-based Radar and Camera Sensor Fusion Architecture for Object Detection Felix Nobis Maximilian Geisslinger Markus Weber Johannes Betz Markus Lienkamp 22 257 0 15 May 2020
Von Mises-Fisher Loss for Training Sequence to Sequence Models with Continuous Outputs Sachin Kumar Yulia Tsvetkov 22 70 0 10 Dec 2018
Conditional Noise-Contrastive Estimation of Unnormalised Models Ciwan Ceylan Michael U. Gutmann 14 41 0 10 Jun 2018
Online normalizer calculation for softmax Maxim Milakov N. Gimelshein 14 84 0 08 May 2018
Language Modeling with Gated Convolutional Networks Yann N. Dauphin Angela Fan Michael Auli David Grangier 50 2,360 0 23 Dec 2016
Efficient softmax approximation for GPUs Edouard Grave Armand Joulin Moustapha Cissé David Grangier Hervé Jégou 25 270 0 14 Sep 2016
The Z-loss: a shift and scale invariant classification loss belonging to the Spherical Family A. D. Brébisson Pascal Vincent 17 10 0 29 Apr 2016
Tree-to-Sequence Attentional Neural Machine Translation Akiko Eriguchi Kazuma Hashimoto Yoshimasa Tsuruoka AIMat 27 269 0 19 Mar 2016