Synchronous bidirectional neural machine translation
Existing approaches to neural machine translation (NMT) generate the target language
sequence token-by-token from left to right. However, this kind of unidirectional decoding …
sequence token-by-token from left to right. However, this kind of unidirectional decoding …
Dependency-to-dependency neural machine translation
Recent research has proven that syntactic knowledge is effective to improve the
performance of neural machine translation (NMT). Most previous work focuses on …
performance of neural machine translation (NMT). Most previous work focuses on …
[HTML][HTML] Synchronous bidirectional inference for neural sequence generation
In sequence to sequence generation tasks (eg machine translation and abstractive
summarization), inference is generally performed in a left-to-right manner to produce the …
summarization), inference is generally performed in a left-to-right manner to produce the …
Neural machine translation with dynamic graph convolutional decoder
Existing wisdom demonstrates the significance of syntactic knowledge for the improvement
of neural machine translation models. However, most previous works merely focus on …
of neural machine translation models. However, most previous works merely focus on …
Hybrid self-attention network for machine translation
The encoder-decoder is the typical framework for Neural Machine Translation (NMT), and
different structures have been developed for improving the translation performance …
different structures have been developed for improving the translation performance …
[PDF][PDF] 面向神经机器翻译的集成学习方法分析
李北, 王强, 肖桐, 姜雨帆, 张哲旸, 刘继强, 张俐… - 中文信息学报, 2019 - cips-cl.org
面向神经机器翻译的集成学习方法分析 Page 1 第** 卷第* 期 中文信息学报 Vol. **,No. * 年* 月
JOURNAL OF CHINESE INFORMATION PROCESSING ***. ,201* 收稿收稿日期:2018-06-10;定稿 …
JOURNAL OF CHINESE INFORMATION PROCESSING ***. ,201* 收稿收稿日期:2018-06-10;定稿 …
Multi-modal and multi-perspective machine translation by collecting diverse alignments
Multi-modal machine translation (MMT) is one of the most active research directions in the
natural language processing. Recently, Seq2Seq translation model with images shows …
natural language processing. Recently, Seq2Seq translation model with images shows …
Efficient bidirectional neural machine translation
The encoder-decoder based neural machine translation usually generates a target
sequence token by token from left to right. Due to error propagation, the tokens in the right …
sequence token by token from left to right. Due to error propagation, the tokens in the right …
[PDF][PDF] 面向维汉神经机器翻译的双向重排序模型分析
张新路, 李晓, 杨雅婷, 王磊, 董瑞 - 北京大学学报(自然科学版), 2020 - tcci.ccf.org.cn
摘要神经机器翻译已经成为机器翻译的主流方法, 但神经机器翻译的拟合训练在维吾尔语到汉语
这种低资源语料库上容易陷入局部最优解, 导致单一模型的翻译结果可能不是全局最优解 …
这种低资源语料库上容易陷入局部最优解, 导致单一模型的翻译结果可能不是全局最优解 …
An empirical study on ensemble learning of multimodal machine translation
With the increasing availability of images, multimodal machine translation (MMT) is leading
a vibrant field. Model structure and multimodal information introduction are the hotspot …
a vibrant field. Model structure and multimodal information introduction are the hotspot …