David Grangier

is this you? claim profile

∙ 0 followers
Google ∙ Facebook

Research Scientist at Facebook

Toward Better Storylines with Sentence-Level Language Models

We propose a sentence-level language model which selects the next senten...
05/11/2020 ∙ by Daphne Ippolito, et al. ∙ 0 ∙ share

read it
BLEU might be Guilty but References are not Innocent

The quality of automatic metrics for machine translation has been increa...
04/13/2020 ∙ by Markus Freitag, et al. ∙ 0 ∙ share

read it
Efficient Content-Based Sparse Attention with Routing Transformers

Self-attention has recently been adopted for a wide range of sequence mo...
03/12/2020 ∙ by Aurko Roy, et al. ∙ 3 ∙ share

read it
Wavesplit: End-to-End Speech Separation by Speaker Clustering

We introduce Wavesplit, an end-to-end speech separation system. From a s...
02/20/2020 ∙ by Neil Zeghidour, et al. ∙ 37 ∙ share

read it
Translationese as a Language in "Multilingual" NMT

Machine translation has an undesirable propensity to produce "translatio...
11/10/2019 ∙ by Parker Riley, et al. ∙ 0 ∙ share

read it
ELI5: Long Form Question Answering

We introduce the first large-scale corpus for long-form question answeri...
07/22/2019 ∙ by Angela Fan, et al. ∙ 0 ∙ share

read it
Tagged Back-Translation

Recent work in Neural Machine Translation (NMT) has shown significant qu...
06/15/2019 ∙ by Isaac Caswell, et al. ∙ 0 ∙ share

read it
Unsupervised Paraphrasing without Translation

Paraphrasing exemplifies the ability to abstract semantic content from s...
05/29/2019 ∙ by Aurko Roy, et al. ∙ 0 ∙ share

read it
fairseq: A Fast, Extensible Toolkit for Sequence Modeling

fairseq is an open-source sequence modeling toolkit that allows research...
04/01/2019 ∙ by Myle Ott, et al. ∙ 0 ∙ share

read it
Modeling Human Motion with Quaternion-based Neural Networks

Previous work on predicting or generating 3D human pose sequences regres...
01/21/2019 ∙ by Dario Pavllo, et al. ∙ 0 ∙ share

read it
3D human pose estimation in video with temporal convolutions and semi-supervised training

In this work, we demonstrate that 3D poses in video can be effectively e...
11/28/2018 ∙ by Dario Pavllo, et al. ∙ 0 ∙ share

read it
Understanding Back-Translation at Scale

An effective method to improve neural machine translation with monolingu...
08/28/2018 ∙ by Sergey Edunov, et al. ∙ 0 ∙ share

read it
Scaling Neural Machine Translation

Sequence to sequence learning models still require several days to reach...
06/01/2018 ∙ by Myle Ott, et al. ∙ 0 ∙ share

read it
QuaterNet: A Quaternion-based Recurrent Model for Human Motion

Deep learning for predicting or generating 3D human pose sequences is an...
05/16/2018 ∙ by Dario Pavllo, et al. ∙ 0 ∙ share

read it
Controllable Abstractive Summarization

Current models for document summarization ignore user preferences such a...
11/14/2017 ∙ by Angela Fan, et al. ∙ 0 ∙ share

read it
Classical Structured Prediction Losses for Sequence to Sequence Learning

There has been much recent work on training neural attention models at t...
11/14/2017 ∙ by Sergey Edunov, et al. ∙ 0 ∙ share

read it
QuickEdit: Editing Text & Translations via Simple Delete Actions

We propose a framework for computer-assisted text editing. It applies to...
11/13/2017 ∙ by David Grangier, et al. ∙ 0 ∙ share

read it
Convolutional Sequence to Sequence Learning

The prevalent approach to sequence to sequence learning maps an input se...
05/08/2017 ∙ by Jonas Gehring, et al. ∙ 0 ∙ share

read it
Language Modeling with Gated Convolutional Networks

The pre-dominant approach to language modeling to date is based on recur...
12/23/2016 ∙ by Yann N. Dauphin, et al. ∙ 0 ∙ share

read it
A Convolutional Encoder Model for Neural Machine Translation

The prevalent approach to neural machine translation relies on bi-direct...
11/07/2016 ∙ by Jonas Gehring, et al. ∙ 0 ∙ share

read it
Iterative Refinement for Machine Translation

Existing machine translation decoding algorithms generate translations i...
10/20/2016 ∙ by Roman Novak, et al. ∙ 0 ∙ share

read it
Vocabulary Selection Strategies for Neural Machine Translation

Classical translation models constrain the space of possible outputs by ...
10/01/2016 ∙ by Gurvan L'Hostis, et al. ∙ 0 ∙ share

read it
Efficient softmax approximation for GPUs

We propose an approximate strategy to efficiently train neural network b...
09/14/2016 ∙ by Edouard Grave, et al. ∙ 0 ∙ share

read it
Interactive Semantic Featuring for Text Classification

In text classification, dictionaries can be used to define human-compreh...
06/24/2016 ∙ by Camille Jandot, et al. ∙ 0 ∙ share

read it
Neural Text Generation from Structured Data with Application to the Biography Domain

This paper introduces a neural model for concept-to-text generation that...
03/24/2016 ∙ by Rémi Lebret, et al. ∙ 0 ∙ share

read it
Strategies for Training Large Vocabulary Neural Language Models

Training neural network language models over large vocabularies is still...
12/15/2015 ∙ by Welin Chen, et al. ∙ 0 ∙ share

read it
ICE: Enabling Non-Experts to Build Models Interactively for Large-Scale Lopsided Problems

Quick interaction between a human teacher and a learning machine present...
09/16/2014 ∙ by Patrice Simard, et al. ∙ 0 ∙ share

read it

David Grangier

Featured Co-authors

Jason Weston

Armand Joulin

Michael Auli

Marc'Aurelio Ranzato

Hervé Jégou

Edouard Grave

Leon Bottou

Angela Fan

Myle Ott

Douglas Eck

Christoph Feichtenhofer

Toward Better Storylines with Sentence-Level Language Models

BLEU might be Guilty but References are not Innocent

Efficient Content-Based Sparse Attention with Routing Transformers

Wavesplit: End-to-End Speech Separation by Speaker Clustering

Translationese as a Language in "Multilingual" NMT

ELI5: Long Form Question Answering

Tagged Back-Translation

Unsupervised Paraphrasing without Translation

fairseq: A Fast, Extensible Toolkit for Sequence Modeling

Modeling Human Motion with Quaternion-based Neural Networks

3D human pose estimation in video with temporal convolutions and semi-supervised training

Understanding Back-Translation at Scale

Scaling Neural Machine Translation

QuaterNet: A Quaternion-based Recurrent Model for Human Motion

Controllable Abstractive Summarization

Classical Structured Prediction Losses for Sequence to Sequence Learning

QuickEdit: Editing Text & Translations via Simple Delete Actions

Convolutional Sequence to Sequence Learning

Language Modeling with Gated Convolutional Networks

A Convolutional Encoder Model for Neural Machine Translation

Iterative Refinement for Machine Translation

Vocabulary Selection Strategies for Neural Machine Translation

Efficient softmax approximation for GPUs

Interactive Semantic Featuring for Text Classification

Neural Text Generation from Structured Data with Application to the Biography Domain

Strategies for Training Large Vocabulary Neural Language Models

ICE: Enabling Non-Experts to Build Models Interactively for Large-Scale Lopsided Problems