
-
Contrastive Learning of General-Purpose Audio Representations
We introduce COLA, a self-supervised pre-training approach for learning ...
read it
-
Human-Paraphrased References Improve Neural Machine Translation
Automatic evaluation comparing candidate translations to human-generated...
read it
-
Toward Better Storylines with Sentence-Level Language Models
We propose a sentence-level language model which selects the next senten...
read it
-
BLEU might be Guilty but References are not Innocent
The quality of automatic metrics for machine translation has been increa...
read it
-
Efficient Content-Based Sparse Attention with Routing Transformers
Self-attention has recently been adopted for a wide range of sequence mo...
read it
-
Wavesplit: End-to-End Speech Separation by Speaker Clustering
We introduce Wavesplit, an end-to-end speech separation system. From a s...
read it
-
Translationese as a Language in "Multilingual" NMT
Machine translation has an undesirable propensity to produce "translatio...
read it
-
ELI5: Long Form Question Answering
We introduce the first large-scale corpus for long-form question answeri...
read it
-
Tagged Back-Translation
Recent work in Neural Machine Translation (NMT) has shown significant qu...
read it
-
Unsupervised Paraphrasing without Translation
Paraphrasing exemplifies the ability to abstract semantic content from s...
read it
-
fairseq: A Fast, Extensible Toolkit for Sequence Modeling
fairseq is an open-source sequence modeling toolkit that allows research...
read it
-
Modeling Human Motion with Quaternion-based Neural Networks
Previous work on predicting or generating 3D human pose sequences regres...
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...
read it
-
Understanding Back-Translation at Scale
An effective method to improve neural machine translation with monolingu...
read it
-
Scaling Neural Machine Translation
Sequence to sequence learning models still require several days to reach...
read it
-
QuaterNet: A Quaternion-based Recurrent Model for Human Motion
Deep learning for predicting or generating 3D human pose sequences is an...
read it
-
Controllable Abstractive Summarization
Current models for document summarization ignore user preferences such a...
read it
-
Classical Structured Prediction Losses for Sequence to Sequence Learning
There has been much recent work on training neural attention models at t...
read it
-
QuickEdit: Editing Text & Translations via Simple Delete Actions
We propose a framework for computer-assisted text editing. It applies to...
read it
-
Convolutional Sequence to Sequence Learning
The prevalent approach to sequence to sequence learning maps an input se...
read it
-
Language Modeling with Gated Convolutional Networks
The pre-dominant approach to language modeling to date is based on recur...
read it
-
A Convolutional Encoder Model for Neural Machine Translation
The prevalent approach to neural machine translation relies on bi-direct...
read it
-
Iterative Refinement for Machine Translation
Existing machine translation decoding algorithms generate translations i...
read it
-
Vocabulary Selection Strategies for Neural Machine Translation
Classical translation models constrain the space of possible outputs by ...
read it
-
Efficient softmax approximation for GPUs
We propose an approximate strategy to efficiently train neural network b...
read it
-
Interactive Semantic Featuring for Text Classification
In text classification, dictionaries can be used to define human-compreh...
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...
read it
-
Strategies for Training Large Vocabulary Neural Language Models
Training neural network language models over large vocabularies is still...
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...
read it