Results 31 to 40 of about 45,590 (288)

Neural Name Translation Improves Neural Machine Translation [PDF]

, 2019
In order to control computational complexity, neural machine translation (NMT) systems convert all rare words outside the vocabulary into a single unk symbol. Previous solution (Luong et al. [1]) resorts to use multiple numbered unks to learn the correspondence between source and target rare words.
Xiaoqing Li, Jinghui Yan, Jiajun Zhang, Chengqing Zong   +3 more
openaire   +1 more source

Lexical Diversity in Statistical and Neural Machine Translation

Information, 2022
Neural machine translation systems have revolutionized translation processes in terms of quantity and speed in recent years, and they have even been claimed to achieve human parity.
Mojca Brglez, Špela Vintar
doaj   +1 more source

Amharic-arabic Neural Machine Translation

5th International Conference on Data Mining and Applications (DMAP 2019), 2019
Many automatic translation works have been addressed between major European language pairs, by taking advantage of large scale parallel corpora, but very few research works are conducted on the Amharic-Arabic language pair due to its parallel data scarcity.
Gashaw, Ibrahim, Shashirekha, H L
openaire   +2 more sources

Progress in Machine Translation

Engineering, 2022
After more than 70 years of evolution, great achievements have been made in machine translation. Especially in recent years, translation quality has been greatly improved with the emergence of neural machine translation (NMT).
Haifeng Wang, Hua Wu, Zhongjun He, Liang Huang, Kenneth Ward Church   +4 more
doaj   +1 more source

Reduction of Neural Machine Translation Failures by Incorporating Statistical Machine Translation

Mathematics, 2023
This paper proposes a hybrid machine translation (HMT) system that improves the quality of neural machine translation (NMT) by incorporating statistical machine translation (SMT).
Jani Dugonik, Mirjam Sepesy Maučec, Domen Verber, Janez Brest   +3 more
doaj   +1 more source

Variational Neural Machine Translation [PDF]

Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, 2016
Models of neural machine translation are often from a discriminative family of encoderdecoders that learn a conditional distribution of a target sentence given a source sentence. In this paper, we propose a variational model to learn this conditional distribution for neural machine translation: a variational encoderdecoder model that can be trained end-
Zhang, Biao, Xiong, Deyi, Su, Jinsong, Duan, Hong, Zhang, Min   +4 more
openaire   +2 more sources

Neural Machine Translation Advised by Statistical Machine Translation

Proceedings of the AAAI Conference on Artificial Intelligence, 2017
Neural Machine Translation (NMT) is a new approach to machine translation that has made great progress in recent years. However, recent studies show that NMT generally produces fluent but inadequate translations (Tu et al. 2016b; 2016a; He et al. 2016; Tu et al. 2017). This is in contrast to conventional Statistical Machine Translation (
Wang, Xing, Lu, Zhengdong, Tu, Zhaopeng, Li, Hang, Xiong, Deyi, Zhang, Min   +5 more
openaire   +2 more sources

Binarized Neural Machine Translation

, 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.
Zhang, Yichi, Garg, Ankush, Cao, Yuan, Lew, Łukasz, Ghorbani, Behrooz, Zhang, Zhiru, Firat, Orhan   +6 more
openaire   +2 more sources

DESIGN OF TRANSLATION AMBIGUITY ELIMINATION METHOD BASED ON RECURRENT NEURAL NETWORKS [PDF]

Acta Informatica Malaysia
The ambiguity of language inevitably leads to the ambiguity of translation, and how to deal with translation ambiguity has become a persistent focus of attention for both human translation and machine translation.
Jianzhou Cui
doaj   +1 more source

Neural Name Translation Improves Neural Machine Translation

, 2016
In order to control computational complexity, neural machine translation (NMT) systems convert all rare words outside the vocabulary into a single unk symbol. Previous solution (Luong et al., 2015) resorts to use multiple numbered unks to learn the correspondence between source and target rare words. However, testing words unseen in the training corpus
Li, Xiaoqing, Zhang, Jiajun, Zong, Chengqing   +2 more
openaire   +2 more sources