Syntax-based Simultaneous Translation through Prediction of Unseen Syntactic Constituents
Syntax-based Simultaneous Translation through Prediction of Unseen Syntactic Constituents
复制标题
DOI：
10.3115/v1/p15-1020
复制
发表时间：
2015-07
期刊：
影响因子：
--
通讯作者：
Yusuke Oda;Graham Neubig;S. Sakti;T. Toda;Satoshi Nakamura
中科院分区：
文献类型：
--
作者：
Yusuke Oda;Graham Neubig;S. Sakti;T. Toda;Satoshi Nakamura
同声翻译是一种通过机器翻译（MT）减少通信延迟的方法，通过在执行翻译之前将输入分成短段。然而，短的段对基于语法的翻译方法提出了问题，因为难以为子段生成准确的解析树。在本文中，我们进行了第一次实验，应用基于语法的SMT同声翻译，并提出了两种方法，以防止降低准确性：一种方法来预测看不见的句法成分，帮助生成完整的解析树，和一种方法，等待更多的输入时，当前的话语是不够的，以生成流畅的翻译。英日翻译的实验表明，所提出的方法可以提高准确性，特别是关于目标句子的词序。
Simultaneous translation is a method to reduce the latency of communication through machine translation (MT) by dividing the input into short segments before performing translation. However, short segments pose problems for syntaxbased translation methods, as it is difficult to generate accurate parse trees for sub-sentential segments. In this paper, we perform the first experiments applying syntax-based SMT to simultaneous translation, and propose two methods to prevent degradations in accuracy: a method to predict unseen syntactic constituents that help generate complete parse trees, and a method that waits for more input when the current utterance is not enough to generate a fluent translation. Experiments on English-Japanese translation show that the proposed methods allow for improvements in accuracy, particularly with regards to word order of the target sentences.