Synchronous Interactive Decoding for Multilingual Neural Machine Translation
文献类型:会议论文
作者 | He H(何灏)![]() |
出版日期 | 2021 |
会议日期 | February 2-9, 2021 |
会议地点 | Virtual Conference |
英文摘要 | To simultaneously translate a source language into multiple different target languages is one of the most common scenarios of multilingual translation. To simultaneously translate a source language into multiple different target languages is one of the most common scenarios of multilingual translation. However, existing methods cannot make full use of translation model information during decoding, such as intra-lingual and inter-lingual future information, and therefore may suffer from some issues like the unbalanced outputs. In this paper, we present a new approach for synchronous interactive multilingual neural machine translation (SimNMT), which predicts each target language output simultaneously and interactively using historical and future information of all target languages. Specifically, we first propose a synchronous cross-interactive decoder in which generation of each target output does not only depend on its generated sequences, but also relies on its future information, as well as history and future contexts of other target languages. Then, we present a new interactive multilingual beam search algorithm that enables synchronous interactive decoding of all target languages in a single model. We take two target languages as an example to illustrate and evaluate the proposed SimNMT model on IWSLT datasets. The experimental results demonstrate that our method achieves significant improvements over several advanced NMT and MNMT models. However, existing methods cannot make full use of translation model information during decoding, such as intra-lingual and inter-lingual future information, and therefore may suffer from some issues like the unbalanced outputs. In this paper, we present a new approach for synchronous interactive multilingual neural machine translation (SimNMT), which predicts each target language output simultaneously and interactively using historical and future information of all target languages. Specifically, we first propose a synchronous cross-interactive decoder in which generation of each target output does not only depend on its generated sequences, but also relies on its future information, as well as history and future contexts of other target languages. Then, we present a new interactive multilingual beam search algorithm that enables synchronous interactive decoding of all target languages in a single model. We take two target languages as an example to illustrate and evaluate the proposed SimNMT model on IWSLT datasets. The experimental results demonstrate that our method achieves significant improvements over several advanced NMT and MNMT models. |
语种 | 英语 |
源URL | [http://ir.ia.ac.cn/handle/173211/45057] ![]() |
专题 | 自动化研究所_模式识别国家重点实验室 博士后_出站报告 |
作者单位 | 1.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China 2.National Laboratory of Pattern Recognition, CASIA, Beijing 100190, China |
推荐引用方式 GB/T 7714 | He H. Synchronous Interactive Decoding for Multilingual Neural Machine Translation[C]. 见:. Virtual Conference. February 2-9, 2021. |
入库方式: OAI收割
来源:自动化研究所
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。