profile picture

David Grangier

Research Scientist @ Apple

nlp applications

machine translation

evaluation

multilinguality

nmt

data selection

data cleaning

mt

diversity

tagging

neural language models

translationese

machine translation system

domain adaption

unsupervised text style transfer

4

presentations

9

number of views

SHORT BIO

David Grangier is a research scientist at Google Research. His current work focuses on algorithms to select valuable training data from auxiliary large, noisy data sets. He also works on improving text generation models, with an emphasis on machine translation.

Presentations

Minimum Bayes Risk Decoding with Neural Metrics of Translation Quality

Markus Freitag and 3 other authors

On Systematic Style Differences between Unsupervised and Supervised MT and an Application for High-Resource Machine Translation

Kelly Marchisio and 2 other authors

A Natural Diet: Towards Improving Naturalness of Machine Translation Output

Markus Freitag and 4 other authors

The Trade-offs of Domain Adaptation for Neural Language Models

David Grangier and 1 other author

Stay up to date with the latest Underline news!

Select topic of interest (you can select more than one)

PRESENTATIONS

  • All Lectures
  • For Librarians
  • Resource Center
  • Free Trial
Underline Science, Inc.
1216 Broadway, 2nd Floor, New York, NY 10001, USA

© 2023 Underline - All rights reserved