Zobrazeno 1 - 10
of 38
pro vyhledávání: '"Dinu, Georgiana"'
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
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
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. We argue that predicting the target word and attributes simultaneously is an effective way
Externí odkaz:
http://arxiv.org/abs/2109.12105
Targeted evaluations have found that machine translation systems often output incorrect gender, even when the gender is clear from context. Furthermore, these incorrectly gendered translations have the potential to reflect or amplify social biases. W
Externí odkaz:
http://arxiv.org/abs/2104.07695
Neural Machine Translation (NMT) models are sensitive to small perturbations in the input. Robustness to such perturbations is typically measured using translation quality metrics such as BLEU on the noisy input. This paper proposes additional metric
Externí odkaz:
http://arxiv.org/abs/2005.00580
A variety of natural language tasks require processing of textual data which contains a mix of natural language and formal languages such as mathematical expressions. In this paper, we take unit conversions as an example and propose a data augmentati
Externí odkaz:
http://arxiv.org/abs/2004.05219
This paper proposes a novel method to inject custom terminology into neural machine translation at run time. Previous works have mainly proposed modifications to the decoding algorithm in order to constrain the output to include run-time-provided tar
Externí odkaz:
http://arxiv.org/abs/1906.01105