Juan Pino

Juan is a Research Scientist at Facebook AI Research in Menlo Park. He studied machine translation at the University of Cambridge. Juan is currently interested in developing end-to-end models for speech translation as well as models that are simultaneous (i.e. they work like human interpreters and begin generating a translation before consuming the entirety of the input text or the input audio).

Juan's Publications

April 07, 2020

RESEARCH

COMPUTER VISION

On Evaluation of Adversarial Perturbations for Sequence-to-Sequence Models

Adversarial examples — perturbations to the input of a model that elicit large changes in the output — have been shown to be an effective way of assessing the robustness of sequence-to-sequence (seq2seq) models. However, these perturbations…

Paul Michel, Xian Li, Graham Neubig, Juan Pino,

April 07, 2020

April 07, 2020

RESEARCH

NLP

Findings of the First Shared Task on Machine Translation Robustness

We share the findings of the first shared task on improving robustness of Machine Translation (MT). The task provides a testbed representing challenges facing MT models deployed in the real world, and facilitates new approaches to improve…

Xian Li, Paul Michel, Antonios Anastasopoulos, Yonatan Belinkov, Nadir Durrani, Orhan Firat, Philipp Koehn, Graham Neubig, Juan Pino, Hassan Sajjad,

April 07, 2020

April 07, 2020

RESEARCH

NLP

The FLORES Evaluation Datasets for Low-Resource Machine Translation: Nepali–English and Sinhala–English

For machine translation, a vast majority of language pairs in the world are considered low-resource because they have little parallel data available. Besides the technical challenges of learning with limited supervision, it is difficult to…

Francisco (Paco) Guzmán, Peng-Jen Chen, Myle Ott, Juan Pino, Guillaume Lample, Philipp Koehn, Vishrav Chaudhary, Marc'Aurelio Ranzato,

April 07, 2020