• Publications
  • Influence
The FLORES Evaluation Datasets for Low-Resource Machine Translation: Nepali–English and Sinhala–English
This work introduces the FLORES evaluation datasets for Nepali–English and Sinhala– English, based on sentences translated from Wikipedia, and demonstrates that current state-of-the-art methods perform rather poorly on this benchmark, posing a challenge to the research community working on low-resource MT.
Monotonic Multihead Attention
This paper proposes a new attention mechanism, Monotonic Multihead Attention (MMA), which extends the monotonic attention mechanism to multihead attention and introduces two novel and interpretable approaches for latency control that are specifically designed for multiple attentions heads.
Fairseq S2T: Fast Speech-to-Text Modeling with Fairseq
State-of-the-art RNN-based as well as Transformer-based models and open-source detailed training recipes are implemented and seamlessly integrated into S2T workflows for multi-task learning or transfer learning.
On Evaluation of Adversarial Perturbations for Sequence-to-Sequence Models
A new evaluation framework for adversarial attacks on seq2seq models that takes the semantic equivalence of the pre- and post-perturbation input into account is proposed and it is shown that performing untargeted adversarial training with meaning-preserving attacks is beneficial to the model in terms of adversarial robustness, without hurting test performance.
VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation
We introduce VoxPopuli, a large-scale multilingual corpus providing 100K hours of unlabelled speech data in 23 languages. It is the largest open data to date for unsupervised representation learning
A Selection Strategy to Improve Cloze Question Quality
We present a strategy to improve the quality of automatically generated cloze and open cloze questions which are used by the REAP tutoring system for assessment in the ill-defined domain of English
SimulMT to SimulST: Adapting Simultaneous Text Translation to End-to-End Simultaneous Speech Translation
This work investigates how to adapt simultaneous text translation methods such as wait-k and monotonic multihead attention to end-to-end simultaneous speech translation by introducing a pre-decision module by designing a novel computation-aware latency metric, adapted from Average Lagging.
SIMULEVAL: An Evaluation Toolkit for Simultaneous Translation
SimulEval is an easy-to-use and general evaluation toolkit for both simultaneous text and speech translation and is equipped with a visualization interface to provide better understanding of the simultaneous decoding process of a system.
Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations and Hardware Implications
Detailed characterizations of deep learning models used in many Facebook social network services are provided and the need for better co-design of algorithms, numerics and computing platforms to address the challenges of workloads often run in data centers is highlighted.
Findings of the First Shared Task on Machine Translation Robustness
The task provides a testbed representing challenges facing MT models deployed in the real world, and facilitates new approaches to improve models’ robustness to noisy input and domain mismatch.