专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20120278060A1 METHOD AND SYSTEM FOR CONFIDENCE-WEIGHTED LEARNING OF FACTORED DISCRIMINATIVE LANGUAGE MODELS 有权
标题翻译：有意义的语言语言模型的信心加权学习方法与系统
公开(公告)号：US20120278060A1
公开(公告)日：2012-11-01
申请号：US13094999
申请日：2011-04-27
申请人： Nicola Cancedda , Viet Ha Thuc
发明人： Nicola Cancedda , Viet Ha Thuc
IPC分类号： G06F17/28
CPC分类号： G06F17/2818 , G10L15/06 , G10L15/197
摘要： A system and method for building a language model for a translation system are provided. The method includes providing a first relative ranking of first and second translations in a target language of a same source string in a source language, determining a second relative ranking of the first and second translations using weights of a language model, the language model including a weight for each of a set of n-gram features, and comparing the first and second relative rankings to determine whether they are in agreement. The method further includes, when the rankings are not in agreement, updating one or more of the weights in the language model as a function of a measure of confidence in the weight, the confidence being a function of previous observations of the n-gram feature in the method.
摘要翻译：提供了一种用于构建翻译系统的语言模型的系统和方法。该方法包括以源语言以相同源字符串的目标语言提供第一和第二翻译的第一相对排名，使用语言模型的权重确定第一和第二翻译的第二相对排名，该语言模型包括一组n-gram特征中的每一个的权重，并且比较第一和第二相对排名以确定它们是否一致。该方法还包括：当排名不一致时，将语言模型中的一个或多个权重作为权重中的置信度的函数来更新，所述置信度是n-gram特征的先前观察值的函数在该方法中。

IPRDB

热门服务

关于我们

友情链接

联系方式