PyTorch: An Imperative Style, High-Performance Deep Learning Library

2 code implementations • NeurIPS 2019 • Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Köpf, Edward Yang, Zach DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, Soumith Chintala

Deep learning frameworks have often focused on either usability or speed, but not both.

Vocal Bursts Intensity Prediction

Training Millions of Personalized Dialogue Agents

1 code implementation • EMNLP 2018 • Pierre-Emmanuel Mazaré, Samuel Humeau, Martin Raison, Antoine Bordes

Current dialogue systems are not very engaging for users, especially when trained end-to-end without relying on proactive reengaging scripted strategies.

Weaver: Deep Co-Encoding of Questions and Documents for Machine Reading

no code implementations • 27 Apr 2018 • Martin Raison, Pierre-Emmanuel Mazaré, Rajarshi Das, Antoine Bordes

This paper aims at improving how machines can answer questions directly from text, with the focus of having models that can answer correctly multiple types of questions and from various types of texts, documents or even from large collections of them.

Open-Domain Question Answering Reading Comprehension