Xian Li

Xian Li is a research scientist working on Machine Translation at Facebook AI. Xian earned her PhD at Rensselaer Polytechnic Institute (RPI) advised by James Hendler. Prior to Facebook, Xian has worked on a variety of machine learning problems at Stitch Fix, Google and Morgan Stanley.

Xian's Publications

October 26, 2020

RESEARCH

NLP

Deep Multilingual Transformer with Latent Depth

The Transformer model has achieved state-of-the-art performance in many sequence modeling tasks. However, how to leverage model capacity with large or variable depths is still an open challenge…

Xian Li , Asa Cooper Stickland, Yuqing Tang, Xiang Kong,

October 26, 2020

November 25, 2019

RESEARCH

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, …

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

November 25, 2019

November 01, 2019

RESEARCH

FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow

Most sequence-to-sequence (seq2seq) models are autoregressive; they generate each token by conditioning on previously generated tokens…

Xian Li, Xuezhe Ma, Chunting Zhou, Graham Neubig, Eduard Hovy

November 01, 2019

June 10, 2019

RESEARCH

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…

Xian Li, Paul Michel, Graham Neubig, Juan Pino

June 10, 2019