公开(公告)号：US20120203539A1

公开(公告)日：2012-08-09

申请号：US13022633

申请日：2011-02-08

申请人： Amittai Axelrod ,  Jianfeng Gao ,  Xiaodong He

发明人： Amittai Axelrod ,  Jianfeng Gao ,  Xiaodong He

IPC分类号： G06F17/28

CPC分类号： G06F17/2809

摘要： Architecture that provides the capability to subselect the most relevant data from an out-domain corpus to use either in isolation or in combination conjunction with in-domain data. The architecture is a domain adaptation for machine translation that selects the most relevant sentences from a larger general-domain corpus of parallel translated sentences. The methods for selecting the data include monolingual cross-entropy measure, monolingual cross-entropy difference, bilingual cross entropy, and bilingual cross-entropy difference. A translation model is trained on both the in-domain data and an out-domain subset, and the models can be interpolated together to boost performance on in-domain translation tasks.

摘要翻译： 架构提供了从外域语料库中选择最相关的数据的能力，以隔离或与域内数据组合使用。 该架构是机器翻译的域适应，从较大的平行翻译句子的一般领域语料库中选择最相关的句子。 选择数据的方法包括单语交叉熵测度，单语交叉熵差，双语交叉熵和双语交叉熵差。 对域内数据和外域子集进行翻译模型的训练，并将这些模型插值到一起，以提升域内翻译任务的性能。

公开(公告)号：US08838433B2

公开(公告)日：2014-09-16

申请号：US13022633

申请日：2011-02-08

申请人： Amittai Axelrod ,  Jianfeng Gao ,  Xiaodong He

发明人： Amittai Axelrod ,  Jianfeng Gao ,  Xiaodong He

IPC分类号： G06F17/28

CPC分类号： G06F17/2809

摘要： An architecture is discussed that provides the capability to subselect the most relevant data from an out-domain corpus to use either in isolation or in combination conjunction with in-domain data. The architecture is a domain adaptation for machine translation that selects the most relevant sentences from a larger general-domain corpus of parallel translated sentences. The methods for selecting the data include monolingual cross-entropy measure, monolingual cross-entropy difference, bilingual cross entropy, and bilingual cross-entropy difference. A translation model is trained on both the in-domain data and an out-domain subset, and the models can be interpolated together to boost performance on in-domain translation tasks.

摘要翻译： 讨论了一种架构，其提供了从外域语料库中选择最相关的数据的能力，以隔离或与域内数据组合使用。 该架构是机器翻译的域适应，从较大的平行翻译句子的一般领域语料库中选择最相关的句子。 选择数据的方法包括单语交叉熵测度，单语交叉熵差，双语交叉熵和双语交叉熵差。 对域内数据和外域子集进行翻译模型的训练，并将这些模型插值到一起，以提升域内翻译任务的性能。