1 code implementation • AMTA 2020 • Tobias Domhan, Michael Denkowski, David Vilar, Xing Niu, Felix Hieber, Kenneth Heafield
We present Sockeye 2, a modernized and streamlined version of the Sockeye neural machine translation (NMT) toolkit.
2 code implementations • Findings (NAACL) 2022 • Maria Nădejde, Anna Currey, Benjamin Hsu, Xing Niu, Marcello Federico, Georgiana Dinu
However, in many cases, multiple different translations are valid and the appropriate translation may depend on the intended target audience, characteristics of the speaker, or even the relationship between speakers.
2 code implementations • 12 Jul 2022 • Felix Hieber, Michael Denkowski, Tobias Domhan, Barbara Darques Barros, Celina Dong Ye, Xing Niu, Cuong Hoang, Ke Tran, Benjamin Hsu, Maria Nadejde, Surafel Lakew, Prashant Mathur, Anna Currey, Marcello Federico
When running comparable models, Sockeye 3 is up to 126% faster than other PyTorch implementations on GPUs and up to 292% faster on CPUs.
1 code implementation • 1 Nov 2023 • Juan Zuluaga-Gomez, Zhaocheng Huang, Xing Niu, Rohit Paturi, Sundararajan Srinivasan, Prashant Mathur, Brian Thompson, Marcello Federico
Conventional speech-to-text translation (ST) systems are trained on single-speaker utterances, and they may not generalize to real-life scenarios where the audio contains conversations by multiple speakers.
1 code implementation • COLING 2018 • Xing Niu, Sudha Rao, Marine Carpuat
Generating natural language requires conveying content in an appropriate style.
1 code implementation • 20 Nov 2019 • Xing Niu, Marine Carpuat
This work aims to produce translations that convey source language content at a formality level that is appropriate for a particular audience.
1 code implementation • 2 Nov 2022 • Anna Currey, Maria Nădejde, Raghavendra Pappagari, Mia Mayer, Stanislas Lauly, Xing Niu, Benjamin Hsu, Georgiana Dinu
As generic machine translation (MT) quality has improved, the need for targeted benchmarks that explore fine-grained aspects of quality has increased.
1 code implementation • NAACL 2019 • Weijia Xu, Xing Niu, Marine Carpuat
Despite some empirical success at correcting exposure bias in machine translation, scheduled sampling algorithms suffer from a major drawback: they incorrectly assume that words in the reference translations and in sampled sequences are aligned at each time step.
1 code implementation • NAACL 2018 • Yogarshi Vyas, Xing Niu, Marine Carpuat
Recognizing that even correct translations are not always semantically equivalent, we automatically detect meaning divergences in parallel sentence pairs with a deep neural model of bilingual semantic similarity which can be trained for any parallel corpus without any manual annotation.
1 code implementation • 24 Sep 2021 • Xing Niu, Georgiana Dinu, Prashant Mathur, Anna Currey
The training data used in NMT is rarely controlled with respect to specific attributes, such as word casing or gender, which can cause errors in translations.
1 code implementation • NAACL 2019 • Xing Niu, Weijia Xu, Marine Carpuat
We aim to better exploit the limited amounts of parallel text available in low-resource settings by introducing a differentiable reconstruction loss for neural machine translation (NMT).
no code implementations • WS 2018 • Xing Niu, Michael Denkowski, Marine Carpuat
Despite impressive progress in high-resource settings, Neural Machine Translation (NMT) still struggles in low-resource and out-of-domain scenarios, often failing to match the quality of phrase-based translation.
no code implementations • EMNLP 2017 • Xing Niu, Marianna Martindale, Marine Carpuat
Stylistic variations of language, such as formality, carry speakers{'} intention beyond literal meaning and should be conveyed adequately in translation.
no code implementations • WS 2017 • Marine Carpuat, Yogarshi Vyas, Xing Niu
Parallel corpora are often not as parallel as one might assume: non-literal translations and noisy translations abound, even in curated corpora routinely used for training and evaluation.
no code implementations • WS 2017 • Xing Niu, Marine Carpuat
Detecting and analyzing stylistic variation in language is relevant to diverse Natural Language Processing applications.
no code implementations • ACL 2020 • Xing Niu, Prashant Mathur, Georgiana Dinu, Yaser Al-Onaizan
Neural Machine Translation (NMT) models are sensitive to small perturbations in the input.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Weijia Xu, Xing Niu, Marine Carpuat
While Iterative Back-Translation and Dual Learning effectively incorporate monolingual training data in neural machine translation, they use different objectives and heuristic gradient approximation strategies, and have not been extensively compared.
no code implementations • IWSLT 2016 • Xing Niu, Marine Carpuat
We describe the University of Maryland machine translation system submitted to the IWSLT 2016 Microsoft Speech Language Translation (MSLT) English-French task.
no code implementations • IWSLT (ACL) 2022 • Antonios Anastasopoulos, Loïc Barrault, Luisa Bentivogli, Marcely Zanon Boito, Ondřej Bojar, Roldano Cattoni, Anna Currey, Georgiana Dinu, Kevin Duh, Maha Elbayad, Clara Emmanuel, Yannick Estève, Marcello Federico, Christian Federmann, Souhir Gahbiche, Hongyu Gong, Roman Grundkiewicz, Barry Haddow, Benjamin Hsu, Dávid Javorský, Vĕra Kloudová, Surafel Lakew, Xutai Ma, Prashant Mathur, Paul McNamee, Kenton Murray, Maria Nǎdejde, Satoshi Nakamura, Matteo Negri, Jan Niehues, Xing Niu, John Ortega, Juan Pino, Elizabeth Salesky, Jiatong Shi, Matthias Sperber, Sebastian Stüker, Katsuhito Sudoh, Marco Turchi, Yogesh Virkar, Alexander Waibel, Changhan Wang, Shinji Watanabe
The evaluation campaign of the 19th International Conference on Spoken Language Translation featured eight shared tasks: (i) Simultaneous speech translation, (ii) Offline speech translation, (iii) Speech to speech translation, (iv) Low-resource speech translation, (v) Multilingual speech translation, (vi) Dialect speech translation, (vii) Formality control for speech translation, (viii) Isometric speech translation.
no code implementations • 19 May 2023 • Benjamin Hsu, Anna Currey, Xing Niu, Maria Nădejde, Georgiana Dinu
While the effect of PLT on quality is well-documented, we highlight a lesser-known effect: PLT can enhance a model's stability to model updates and input perturbations, a set of properties we call model inertia.
no code implementations • 26 May 2023 • Gabriele Sarti, Phu Mon Htut, Xing Niu, Benjamin Hsu, Anna Currey, Georgiana Dinu, Maria Nadejde
Attribute-controlled translation (ACT) is a subtask of machine translation that involves controlling stylistic or linguistic attributes (like formality and gender) of translation outputs.