.png){kind=icon}
返回
Improving tree-based neural machine translation with dynamic lexicalized dependency encoding
.png){kind=icon}
PRE
AI
DOI：10.1016/j.knosys.2019.105042.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Tree-to-sequence neural machine translation models have proven to be effective in learning the semantic representations from the exploited syntactic structure. Despite their success, tree-to-sequence models have two major issues: (1) the embeddings of constituents at the higher tree levels tend to contribute less in translation; and (2) using a single set of model parameters is difficult to fully capture the syntactic and semantic richness of linguistic phrases. To address the first problem, we proposed a lexicalized dependency model, in which the source-side lexical representations are learned in a head-dependent fashion following a dependency graph. Since the number of dependents is variable, we proposed a variant recurrent neural network (RNN) to jointly consider the long-distance dependencies and the sequential information of words. Concerning the second problem, we adopt a latent vector to dynamically condition the parameters for the composition of each node representation. Experimental results reveal that the proposed model significantly outperforms the recently proposed tree-based methods in English-Chinese and English-German translation tasks with even far fewer parameters. (C) 2019 Elsevier B.V. All rights reserved.
Keyword:
Syntactic modeling
Dynamic parameters
Tree-RNN
Neural machine translation (NMT)
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
K
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
.png){kind=icon}
分享收藏分享收藏
分享收藏
查看更多内容