Results 11 to 20 of about 53,972 (305)
Revista Tradumàtica, 2017 From the outset, automatic translation was dominated by systems based on linguistic information, but then later other approaches opened up the way, such as translation memories and statistical machine translation which draw on parallel language corpora ...
Francisco Casacuberta Nolla +1 more
doaj +3 more sources
Translating Akkadian to English with neural machine translation. [PDF]
PNAS Nexus, 2023 Abstract Cuneiform is one of the earliest writing systems in recorded human history (ca. 3,400 BCE–75 CE). Hundreds of thousands of such texts were found over the last two centuries, most of which are written in Sumerian and Akkadian.
Gutherz G +4 more
europepmc +3 more sources
Neural Machine Translation of Basque [PDF]
, 2018 We describe the first experimental results in neural machine translation for Basque. As a synthetic language featuring agglutinative morphology, an extended case system, complex verbal morphology and relatively free word order, Basque presents a large ...
Etchegoyhen, Thierry +9 more
core +3 more sources
Sublemma-Based Neural Machine Translation [PDF]
Complexity, 2021 Powerful deep learning approach frees us from feature engineering in many artificial intelligence tasks. The approach is able to extract efficient representations from the input data, if the data are large enough. Unfortunately, it is not always possible
Thien Nguyen, Huu Nguyen, Phuoc Tran
doaj +2 more sources
Incorporating bilingual translation templates into neural machine translation [PDF]
Scientific ReportsIn the neural machine translation (NMT) paradigm, transformer-based NMT has achieved great progress in recent years. It uses parallel corpus and is based on the stand end-to-end structure.
Fuxue Li +5 more
doaj +2 more sources
Investigating Backtranslation in Neural Machine Translation [PDF]
CoRR, 2018 A prerequisite for training corpus-based machine translation (MT) systems – either Statistical MT (SMT) or Neural MT (NMT) – is the availability of high-quality parallel data.
Shterionov, Dimitar +4 more
core +6 more sources
Domain robustness in neural machine translation [PDF]
CoRR, 2020 Translating text that diverges from the training domain is a key challenge for machine translation. Domain robustnes - the generalization of models to unseen test domains - is low for both statistical (SMT) and neural machine translation (NMT).
Müller, Mathias; https://orcid.org/ +2 more
core +6 more sources
Neural pre-translation for hybrid machine translation [PDF]
, 2017 Hybrid machine translation (HMT) takes advantage of different types of machine translation (MT) systems to improve translation performance. Neural machine translation (NMT) can produce more fluent translations while phrase-based statistical machine ...
Way, Andy, Du, Jinhua
core +3 more sources
Binarized Neural Machine Translation
Advances in Neural Information Processing Systems 36, 2023 The rapid scaling of language models is motivating research using low-bitwidth quantization. In this work, we propose a novel binarization technique for Transformers applied to machine translation (BMT), the first of its kind. We identify and address the problem of inflated dot-product variance when using one-bit weights and activations.
Yichi Zhang 0006 +6 more
openaire +3 more sources
Translating Phrases in Neural Machine Translation [PDF]
Proceedings of the 2017 Conference on Empirical Methods in Natural
Language Processing, 2017 Accepted by EMNLP ...
Xing Wang 0007 +3 more
openaire +2 more sources