Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Nadejde, Maria"'
Autor:
Nădejde, Maria
Machine Translation (MT) for language pairs with long distance dependencies and word reordering, such as German-English, is prone to producing output that is lexically or syntactically incoherent. Statistical MT (SMT) models used explicit or latent s
Externí odkaz:
https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.756627
Autor:
Hsu, Benjamin, Liu, Xiaoyu, Li, Huayang, Fujinuma, Yoshinari, Nadejde, Maria, Niu, Xing, Kittenplon, Yair, Litman, Ron, Pappagari, Raghavendra
Document translation poses a challenge for Neural Machine Translation (NMT) systems. Most document-level NMT systems rely on meticulously curated sentence-level parallel data, assuming flawless extraction of text from documents along with their preci
Externí odkaz:
http://arxiv.org/abs/2406.08255
Autor:
Sarti, Gabriele, Htut, Phu Mon, Niu, Xing, Hsu, Benjamin, Currey, Anna, Dinu, Georgiana, Nadejde, Maria
Publikováno v:
Proceedings of ACL (2023) 1476-1490
Attribute-controlled translation (ACT) is a subtask of machine translation that involves controlling stylistic or linguistic attributes (like formality and gender) of translation outputs. While ACT has garnered attention in recent years due to its us
Externí odkaz:
http://arxiv.org/abs/2305.17131
Like many other machine learning applications, neural machine translation (NMT) benefits from over-parameterized deep neural models. However, these models have been observed to be brittle: NMT model predictions are sensitive to small input changes an
Externí odkaz:
http://arxiv.org/abs/2305.11808
Autor:
Currey, Anna, Nădejde, Maria, Pappagari, Raghavendra, Mayer, Mia, Lauly, Stanislas, Niu, Xing, Hsu, Benjamin, Dinu, Georgiana
As generic machine translation (MT) quality has improved, the need for targeted benchmarks that explore fine-grained aspects of quality has increased. In particular, gender accuracy in translation can have implications in terms of output fluency, tra
Externí odkaz:
http://arxiv.org/abs/2211.01355
This paper addresses the task of contextual translation using multi-segment models. Specifically we show that increasing model capacity further pushes the limits of this approach and that deeper models are more suited to capture context dependencies.
Externí odkaz:
http://arxiv.org/abs/2210.10906
Autor:
Hieber, Felix, Denkowski, Michael, Domhan, Tobias, Barros, Barbara Darques, Ye, Celina Dong, Niu, Xing, Hoang, Cuong, Tran, Ke, Hsu, Benjamin, Nadejde, Maria, Lakew, Surafel, Mathur, Prashant, Currey, Anna, Federico, Marcello
Sockeye 3 is the latest version of the Sockeye toolkit for Neural Machine Translation (NMT). Now based on PyTorch, Sockeye 3 provides faster model implementations and more advanced features with a further streamlined codebase. This enables broader ex
Externí odkaz:
http://arxiv.org/abs/2207.05851
The machine translation (MT) task is typically formulated as that of returning a single translation for an input segment. However, in many cases, multiple different translations are valid and the appropriate translation may depend on the intended tar
Externí odkaz:
http://arxiv.org/abs/2205.04022
Autor:
Nadejde, Maria, Tetreault, Joel
Publikováno v:
Proceedings of the 2019 EMNLP Workshop W-NUT: The 5th Workshop on Noisy User-generated Text, pages 27-33, Hong Kong, Nov 4, 2019
Grammar error correction (GEC) systems have become ubiquitous in a variety of software applications, and have started to approach human-level performance for some datasets. However, very little is known about how to efficiently personalize these syst
Externí odkaz:
http://arxiv.org/abs/2006.02964
Autor:
Sennrich, Rico, Firat, Orhan, Cho, Kyunghyun, Birch, Alexandra, Haddow, Barry, Hitschler, Julian, Junczys-Dowmunt, Marcin, Läubli, Samuel, Barone, Antonio Valerio Miceli, Mokry, Jozef, Nădejde, Maria
We present Nematus, a toolkit for Neural Machine Translation. The toolkit prioritizes high translation accuracy, usability, and extensibility. Nematus has been used to build top-performing submissions to shared translation tasks at WMT and IWSLT, and
Externí odkaz:
http://arxiv.org/abs/1703.04357