Juan Pino

Research Scientist

I’m a research scientist at Facebook working on neural machine translation and language modeling. I obtained my PhD from the University of Cambridge under the supervision of Bill Byrne where I developed a new model for translation grammar extraction from word alignment models and built translation systems that obtained the best automatic score at WMT10 and WMT13 in the French-English and Russian-English tracks.


Machine translation, language modeling and natural language processing

Latest Publications

EMNLP - November 9, 2020

SIMULEVAL : An Evaluation Toolkit for Simultaneous Translation

Xutai Ma, Mohammad Javad Dousti, Changhan Wang, Jiatao Gu, Juan Pino

COLING - November 9, 2020

Dual-decoder Transformer for Joint Automatic Speech Recognition and Multilingual Speech Translation

Hang Le, Juan Pino, Changhan Wang, Jiatao Gu, Didier Schwab, Laurent Besacier

Interspeech - November 9, 2020

Self-Training for End-to-End Speech Translation

Juan Pino, Qiantong Xu, Xutai Ma, Mohammad Javad Dousti, Yun Tang

LREC - July 17, 2020

CoVoST: A Diverse Multilingual Speech-To-Text Translation Corpus

Changhan Wang, Juan Pino, Anne Wu, Jiatao Gu

ICASSP - May 7, 2020

SkinAugment: Auto-Encoding Speaker Conversions for Automatic Speech Translation

Arya D. McCarthy, Liezl Puzon, Juan Pino

ICLR - April 29, 2020

Monotonic Multihead Attention

Juan Pino, James Cross, Liezl Puzon, Jiatao Gu, Xutai Ma

WMT - November 25, 2019

Findings of the First Shared Task on Machine Translation Robustness

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

EMNLP - October 31, 2019

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

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

WMT at ACL - August 2, 2019

Findings of the WMT 2019 Shared Task on Parallel Corpus Filtering for Low-Resource Conditions

Philipp Koehn, Francisco (Paco) Guzman, Vishrav Chaudhary, Juan Pino

NAACL - June 10, 2019

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

Paul Michel, Xian Li, Graham Neubig, Juan Pino

ArXiv - November 24, 2018

Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations and Hardware Implications

Jongsoo Park, Maxim Naumov, Protonu Basu, Summer Deng, Aravind Kalaiah, Daya Khudia, James Law, Parth Malani, Andrey Malevich, Satish Nadathur, Juan Pino, Martin Schatz, Alexander Sidorov, Viswanath Sivakumar, Andrew Tulloch, Xiaodong Wang, Yiming Wu, Hector Yuen, Utku Diril, Dmytro Dzhulgakov, Kim Hazelwood, Bill Jia, Yangqing Jia, Lin Qiao, Vijay Rao, Nadav Rotem, Sungjoo Yoo, Mikhail Smelyanskiy